Events

Aug 13 - Aug 19, 2023

• 

  Tackling the Communication Bottlenecks of Distributed Deep Learning Training Workloads

  Chen-Yu (Elton) Ho, Ph.D. Student, Computer Science

  Aug 14, 08:00 - 10:00

  B2 L5 R5220

  This presentation will focus on addressing the communication bottlenecks in distributed deep learning (DDL) training workloads. Deep neural networks (DNNs) are widely used in various domains, but training them can be time-consuming, especially with large models and datasets. Three innovative solutions are proposed and evaluated in the dissertation.

Jul 30 - Aug 5, 2023

• 

  Hybrid Analysis and Modeling as an Enabler for Digital Twins

  Prof. Adil Rasheed, Computer Science and Engineering, Norwegian University of Science and Technology

  Aug 3, 11:00 - 12:00

  B1 L4 R4214

  hybrid modelling

  During this talk, we will delve into a new paradigm in modeling, called Hybrid Analysis and Modeling, which has the ability to combine the best of both the physics-driven and data-driven worlds, while eliminating their weaknesses. This approach has shown remarkable utility in the context of digital twin technology and will be demonstrated through a lab-scale experimental setup, mimicking building energy modeling.

Jul 16 - Jul 22, 2023

• 

  Prioritizing Causative Genomic Variants by Integrating Molecular and Functional Annotations from Multiple Biomedical Ontologies

  Azza Althagafi, Ph.D. Student, Computer Science

  Jul 20, 13:00 - 17:00

  B2 L5 R5220

  The dissertation focuses on developing novel computational methods to improve the diagnosis of patients with rare or complex diseases. By systematically relating human phenotypes resulting from gene function loss or change to gene functions and anatomical/cellular locations, the candidate aims to enhance the prediction and prioritization of disease-causing variants. These methods, leveraging graph-based machine learning and biomedical ontologies, demonstrate significant improvements over existing approaches. The presentation will include a systematic evaluation of the methods, demonstrating their ability to compensate for incomplete data and their applications in biomedicine and clinical decision-making. This research contributes to more effective methods for predicting disease-causing variants and advancing precision medicine, offering promising prospects for improved diagnostics and patient care.
• 

  Ontology design patterns and methods for integrating phenotype ontologies

  Sarah Alghamdi, Ph.D. Student, Computer Science

  Jul 20, 09:00 - 10:00

  B3 L5 R5209.

  bio-ontology phenotype ontologies

  Ontologies are widely used in various domains, including biomedical research, to structure information, represent knowledge, and analyze data. Combining ontologies from different domains is crucial for systematic data analysis and comparison of similar domains. This requires ontology composition, integration, and alignment, which involve creating new classes by reusing classes from different domains, aggregating types of ontologies within the same domain, and finding correspondences between ontologies within the same or similar domain.

Jun 4 - Jun 10, 2023

• 

  Exploiting Data Sparsity in Matrix Algorithms for Adaptive Optics and Seismic Imaging

  Yuxi Hong, Ph.D. Student, Computer Science

  Jun 7, 14:30 - 17:00

  B2 R5209;

  Matrix Algorithms machine learning High Performance Computing

  This thesis addresses the exponential growth of experimental data and the resulting computational complexity seen in two major scientific applications, which account for most cycles consumed on today's supercomputers.

May 21 - May 27, 2023

• 

  Assessing DNS Resilience and Robustness

  Prof. Fatemah Alharbi, Assistant Professor, the Computer Science Department, Taibah University, Yanbu, KSA.

  May 25, 15:30 - 16:30

  B4 L5 R5220.

  resilience Robustness

  The Domain Name System (DNS) is a core protocol for the Internet. It resolves mappings between Internet Protocol (IP) addresses and their corresponding Fully Qualified Domain Names (FQDNs). Since all Internet communications rely on it, DNS structuring should therefore be resilient and robust against failure to avoid any service interruption. While the research community and experienced practitioners have established best practices to this end, many worldwide DNS implementations are still prone to many types of configuration errors. In this talk, I discuss the adoption of these approaches in some countries. Also, a case study is presented considering domains in Saudi Arabia (.sa) that illustrates the value of measuring the DNS at this scale. The results are valuable to improve the DNS infrastructure in the kingdom. Lastly, I provide recommendations to improve DNS service resilience and robustness.

May 7 - May 13, 2023

• 

  Towards the Inference, Understanding, and Reasoning on Edge Devices

  Guoqing Ma, Ph.D. Student, Computer Science

  May 10, 14:00 - 16:00

  B1 L3 R3119

  Edge devices refer to compact hardware that performs data processing and analysis close to the data source, eliminating the need for data transmission to centralized systems for analysis. These devices are typically integrated into other equipment, such as sensors or smart appliances, and can collect and process data in real time.
• 

  Extraction of Complex DNN Models: Real Threat or Boogeyman? - Graduate Seminar

  Prof.N.Asokan, Computer Science, University of Waterloo

  May 8, 12:00 - 13:00

  B9 L2 H2 H2

  complex models Deep learning model extraction

  The success of deep learning in many application domains has been nothing short of dramatic. The success has brought the spotlight onto security and privacy concerns with deep learning. One of them is the threat of "model extraction": when a machine learning model is made available to customers via an inference interface, a malicious customer can use repeated queries to this interface and use the information gained to construct a surrogate model. In this talk, I will describe our work in exploring whether model extraction constitutes a realistic threat. I will also discuss possible countermeasures, focussing on deterrence mechanisms that allow for the verification of ownership of ML models.

Apr 30 - May 6, 2023

• 

  Bringing the Cloud to industrial systems: trends, opportunities and challenges

  Marcello Cinque, Associate Professor, Computer Engineering, the University of Naples Federico Il, Italy.

  May 4, 15:30 - 16:30

  B4 L5 R5209

  cloud technologies industrial systems

  In recent years we are witnessing the advent of service computing and cloud technologies in industrial applications, with intriguing innovations and novel compelling challenges. For instance, in the automotive, there are initiatives for consolidating Electronic Control Units (ECUs) as virtual machines on the same board. Or in the Industry 4.0 (I4.0), researchers and practitioners are dealing with the challenge of making the factory floor programmable by softwarizing hardware elements with edge-cloud native components. The talk will delve into this novel trend, discussing enabling virtualization technologies for industrial systems, including hypervisors, real-time container-based solutions, and software orchestration approaches.
• 

  Towards Data-efficient Graph Learning

  Qiannan Zhang, Ph.D. Student, Computer Science

  May 2, 18:00 - 20:00

  KAUST

  This dissertation focuses on the challenge of learning with small amounts of annotated data in graph machine learning. The scarcity of annotated data can severely degrade the performance of graph learning models, and the ability to learn with small amounts of data, known as data-efficient graph learning, is essential for achieving strong generalization in low-data regimes. The dissertation proposes three methods to address the challenges of graph learning in low-data scenarios, including a graph meta-learning framework, a solution for few-shot graph classification, and a cross-domain knowledge transfer model. Experimental results demonstrate the effectiveness of the proposed methods in improving model generalization for data-efficient graph learning.
• 

  Robust and Energy-Efficient Embedded Computing

  Semeen Rehman, Assistant Professor, Electrical Engineering and Information Technology, TU Wien

  May 1, 12:00 - 13:00

  B9 L1 R3131

  Embedded systems are currently an indispensable part of our lives because of their pervasive deployment in a wide range of critical applications (e.g., automotive, encryption, and healthcare, etc.) as well as non-critical applications (e.g., image/video processing, etc.). These embedded system form the fundamental components of today’s Cyber Physical Systems (CPS) and Internet-of-Things (IoT), which are subjected to stringent constraints in terms of reliability, security, and power-/energy especially in case of battery-driven scenarios. Due to the shrinking transistor dimensions, embedded computing hardware are increasingly susceptible to a wide range of reliability threats e.g., transient faults (such as soft errors due to high-energy particle strikes) and permanent faults due to design-time process variations and run-time aging effects. These threats may lead to functional and timing errors that may jeopardize the correct application’s executions. Furthermore, security has also become a crucial aspect in today’s systems because of several security threats, e.g., confidentiality threat to steal the IP or private information via side channel attacks. These reliability and security threats may lead to a catastrophic impact on the robustness of embedded systems. Another key design constraint of a battery-driven embedded platform is power-/energy-wise efficiency, e.g., a device under a low power/battery mode during the critical application execution may miss a critical event that may lead to a catastrophic outcome. In order to address the above-mentioned challenges, it is crucial to investigate different techniques at the hardware and software layers. In this talk, I will first highlight the key robustness and energy efficiency challenges in embedded computing systems, and will present techniques to address these challenges.
• 

  Towards a Universal Knowledge Graph Chatbot: ChatGPT versus Traditional Question Answering for Knowledge Graphs

  Prof.Essam Mansour, Computer Science and Software Engineering, Concordia University

  May 1, 12:00 - 13:00

  B9 L2 H2 H2

  ChatGPT conversational AI QASs knowledge graphs

  Conversational AI and Question-Answering systems (QASs) for knowledge graphs (KGs) are both emerging research areas: they empower users with natural language interfaces for extracting information efficiently and effectively. While Conversational AI simulates human-like conversations, its effectiveness is limited by the available training data. However, QASs retrieve the most up-to-date information from KGs by translating natural language queries into formal queries that the database engine can process. In this talk, we examine the characteristics of existing approaches for combining Conversational AI and QASs to create novel KG chatbots. We also introduce KGQAn, a universal QA system that can be applied to any KG without the need for customization.
• 

  Multimodal Video Analysis

  Juan Carlos L. Alcazar, Postdoctoral Research Fellow, Image and Video Understanding Lab

  Apr 30, 12:00 - 13:00

  B9 L2 H2

  Multimodal Video Analysis

  The recognition of human behavior has driven most advances in video analysis over the past decade.

Apr 16 - Apr 22, 2023

• 

  Latent Space Manipulation of GANs for Seamless Image Compositing

  Anna Fruehstueck, Ph.D., Computer Science

  Apr 17, 17:30 - 18:30

  B5 L5 R5220

  Generative Adversarial Networks image synthesis texture synthesis

  Generative Adversarial Networks (GANs) are a very successful method for high-quality image synthesis and are a powerful tool to generate realistic images by learning their visual properties from a dataset of exemplars. However, the controllability of the generator output still poses many challenges. In this thesis, we propose several methods for achieving larger and/or higher visual quality in GAN outputs by combining latent space manipulations with image compositing operations
• 

  Serverless Computing: With Great Freedom Comes Great Opportunity!

  Marco Canini, Professor, Computer Science

  Apr 17, 12:00 - 13:00

  B9 L2 H2 H2

  serverless computing

  This talk introduces serverless computing, a programming model that has flourished in the last few years, mainly because it allows developers to concentrate on the application logic and not worry about scalability and resource management. Current serverless offerings give users limited flexibility for configuring the resources allocated to their function invocations. We take a principled approach to the problem of resource allocation for serverless functions, analyzing the effects of automating this choice in a way that leads to the best combination of performance and cost.

Apr 9 - Apr 15, 2023

• 

  A personal path from mathematics to biomedical research

  Apr 12, 12:00 - 13:00

  B2 L5 R5209

  Biomedical Computational biology

  A personal presentation describing the role of computational biology and bioinformatics in addressing state-of-the-art biomedical challenges. First, I will provide an overview of the transition between a Ph.D. in Mathematics to a postdoc in Computational Biology: How did it happen? What were the challenges? Secondly, I will briefly present several current case studies where computational biology (in several flavors) is core to understanding novel biological data related to multi-omic data analysis, spatial profiling, gene therapy, and more.
• 

  Web-based 3D Visualization

  Ivan Viola, Professor, Computer Science

  Apr 10, 12:00 - 13:00

  B9 L2 H2 H2

  nanovisualization computer graphics 3D graphics WebGPU WebAssmbly

  In this seminar I will present how to create 3D computer graphics and visualization systems for the web, using WebAssmbly and WebGPU language specifications, which are new, bleeding-edge technologies. Previously, accelerated graphics on the web was based on JavaScript libraries, which is still very popular, but they do not offer detailed memory management and code optimization, necessary for systems requiring high memory load and high computational demands. WebAssembly and WebGPU can be compiled from the C++ or Rust code, which also allows the deployment of the same codebase either for web or for the desktop-based applications.

Apr 2 - Apr 8, 2023

• 

  Cybersecurity of Industrial Control Systems - Challenges and Research Directions

  Awais Rashid, Professor of Cybersecurity, the University of Bristol, Director of the EPSRC Centre for Doctoral Training in Trust, Identity, Privacy and Security in Large-Scale Infrastructures

  Apr 3, 12:00 - 13:00

  B9 L2 H2 H2.

  cybersecurity industrial control systems

  This Distinguished Lecture is part of the CS Graduate Seminars. Abstract Industrial Control Systems play an important role in monitoring, controlling, and automating critical infrastructure such as water, gas, oil, and electricity. Recent years have seen a number of high-profile cyber attacks on such infrastructure, exemplified by Triton, Colonial Pipeline, and the Ukrainian Power Grid attacks. This naturally begs the question: how should we manage cyber security risks in such infrastructure on which the day-to-day functioning of our society relies? What are the complexities of managing

Mar 26 - Apr 1, 2023

• 

  End-to-Same-End Encryption: Modularly Augmenting an App with an Efficient, Portable, and Blind Cloud Storage

  Qiang Tang, Senior Lecturer (equal to U.S. Associate Professor), the University of Sydney

  Mar 30, 12:00 - 13:00

  B4 L5 R5220.

  cloud storage End-to-Same-End-Encryption

  Cloud storage is pervasive nowadays; surprisingly, how to secure cloud storage that is usable in the real world is in fact still open. In this work, we propose a novel system called End-to-Same-End Encryption (E2SEE) that can be deployed directly on existing infrastructure and provide both security and usability. Our system can be flexibly used to augment any App with secure storage, for users to create a personal digital lockbox, and for the cloud to provide secure storage service. A preliminary version of E2SEE was deployed in Snapchat, serving hundreds of millions of users, and the research result was published at USENIX Security 22.
• 

  Challenges in ML for Sustainable Development

  Prof. Laure Berti, Computer Science, Research Director, French Institute of Research for Sustainable Development (IRD)

  Mar 28, 14:00 - 15:00

  B1 L4 R4214

  data cleaning and preparation data fusion

  This talk will present recent approaches for mitigation and adaptation, for which data analytics and ML are parts of the solution in a larger context of interdisciplinary and methodological research and innovations.
• 

  Thoughts on software and systems engineering - 2023-03-27

  Eric Feron, Professor, Electrical and Computer Engineering

  Mar 27, 12:00 - 13:00

  B9 L2 H2 H2

  Complex systems and software engineering, and associated challenges become increasingly important for the well-being and safety of our society of humans. Motivated by this push towards ever more complex systems and software of all sizes, spectacular failures, and decades of questioning in a variety of contexts and endeavors, this talk presents a theory of complex systems engineering, that is, a scientific theory in which an engineered system or software can be seen as a validated scientific hypothesis arising from a convergent mix of mathematical and validated experimental constructs. In its simplest form, a complex engineered system is a manufactured, validated scientific hypothesis arising from a mathematical theorem similar to those found in theoretical physics. This observation provides suggestions for improving system design, especially system architecture, by leveraging advanced mathematical and / or scientific concepts. In return, mathematicians and computer scientists can benefit from this bridge to engineering by bringing to bear many of their automated and manual theorem proving techniques to help with the design of complex systems.

Mar 19 - Mar 25, 2023

• 

  Making federated learning practical and confidential

  Dr. Ruichuan Chen, Distinguished Member of Technical Staff and a Tech Lead, Nokia Bell Labs

  Mar 23, 15:30 - 16:30

  B4 L5 R5209

  Federated learning

  Federated learning (FL) is increasingly deployed among multiple clients to train a shared model over decentralized data. To address the privacy concerns, FL systems need to protect the clients' data from being revealed during training, and also control data leakage through trained models when exposed to untrusted domains. However, existing FL systems (with distributed differential privacy) work impractically in the presence of client dropout, resulting in either poor privacy guarantees or degraded training accuracy. In addition, existing FL systems focus on safeguarding the privacy of training data, but not on protecting the confidentiality of the models being trained, which are increasingly of high business value. In this talk, I will present two pieces of our recent work that aim to address these aforementioned issues.
• 

  Interpretation, Verification and Privacy Techniques for Improving the Trustworthiness of Neural Networks

  Arnaud Dethise, Ph.D. Student, Computer Science

  Mar 22, 12:30 - 14:30

  B1 L3 R3119

  This presentation addresses the challenges associated with trusting Neural Networks due to their black-box nature and limited ability to answer important questions on how they behave. The thesis proposes techniques that increase the trustworthiness of Neural Network models by employing approaches to overcome their black-box nature. The techniques include efficient extraction and verification of weights and decisions to ensure correctness with regards to pre-existing properties, continuous and exact explanations of the model behavior, and scalable training techniques providing strong, theoretically provable guarantees of privacy. We provide strong, approximation-free guarantees about Neural Networks, improving their trustworthiness to make it more likely that users will be willing to deploy them in the real world.
• 

  Tackling credential abuse together

  Michael Reiter, James B. Duke Distinguished Professor, Departments of Computer Science and Electrical & Computer Engineering, Duke University

  Mar 20, 12:00 - 13:00

  B9 L2 H2 H2.

  data security

  Despite long-ago predictions (e.g., see Bill Gates, 2004) that other user-authentication technologies would replace passwords, passwords remain not only pervasive but have flourished as the dominant form of account protection, especially at websites such as retailers that require a low-friction user experience. This talk will describe our research on methods to tackle three key ingredients of account takeovers for password-protected accounts today: (i) site database breaches, which is the largest source of stolen passwords for internet sites; (ii) the tendency of users to reuse the same or similar passwords across sites; and (iii) credential stuffing, in which attackers submit breached credentials for one site in login attempts for the same users' accounts at another.

Mar 12 - Mar 18, 2023

• 

  Robust Geometry Processing for Physical Simulation

  Prof.Daniele Panozzo

  Mar 13, 15:45 - 16:45

  B4 L5 R5209

  geometry processing physical simulation

  I will discuss the limitations of the current state of the art, and present a proposal for an integrated pipeline, considering data acquisition, meshing, basis design, and numerical optimization as a single challenge, where tradeoffs can be made between different phases to increase automation and efficiency. I will demonstrate that this integrated approach offers many advantages, while opening exciting new geometry processing challenges, and that a fully opaque meshing and analysis solution is already possible for heat transfer and elasticity problems with contact. I will present a set of applications enabled by this approach in reinforcement learning for robotics, force measurements in biology, shape design in mechanical engineering, stress estimation in biomechanics, and simulation of deformable objects in graphics.
• 

  Inter-Surface Maps

  Prof.Leif Kobbelt

  Mar 13, 14:30 - 15:30

  B4 L5 R5209

  inter-surface maps 3D shapes

  Many tasks in the analysis and synthesis of (collections of) 3D shapes boils down to computing a map between two surfaces. Such inter-surface maps can be used to establish correspondences, to transfer information or annotation from one object to another, or to plausibly deform one shape into another. If the two shapes are represented as polygon meshes, a continuous inter-surface map does not only assign the vertices of the source mesh to the target mesh but also maps the interior of the triangles which adds to the complexity of the task.
• 

  Discrete Surfaces from Developable Strips

  Prof.Christian Müller

  Mar 13, 13:30 - 14:30

  B4 L5 R5209

  Geometry geometry processing developable strips

  We will discuss several settings in which smooth developable strips are attached to each other or assembled in some other way to obtain surfaces with interesting geometric properties. Driven by the view towards applications we will investigate collections of strips which lie orthogonal or tangential to a reference surface and assume particular shapes. Such strips can serve as support structures or cladding panels of free-form shapes in architectural contexts. Our focus will lie on surfaces with a constant ratio of principal curvatures, cone nets, geodesic grid shells, and others.
• 

  Computing in the Specialization Era

  Prof.Gustavo Alonso, Computer Science, ETH Zurich

  Mar 13, 12:00 - 13:00

  B9 L2 H2 H2

  cloud computing FPGA Hardware acceleration

  In this talk I will discuss the shift towards hardware acceleration and show with several examples from industry and from research the large role that FPGAs are playing. I will hypothesize that we are in a new era where most of the established assumptions, rules of thumb, and accumulated wisdom about many aspects of computation in general and of data processing in particular no longer hold and need to be revisited.
• 

  Cohomology in fluids

  Prof.Albert Chern

  Mar 13, 11:15 - 12:15

  B4 L5 R5209

  fluids cohomology fluid dynamics Geometry geometry processing

  We present a topological analysis of the vorticity formulation in describing fluid dynamics. Despite its widespread use in fluid mechanics, this formulation is insufficient at describing fluid dynamics on a non-simply-connected domain. What is missing is an equation of motion for fluid's cohomology component, which exhibits fascinating dynamics previously under explored. Using geometric language, we derive the new equation of motion and establish new conservation laws, as Casimir invariants in Hamiltonian mechanics, for fluids on domains with general topology. Significantly, we present the first physically correct vortex method on curved surfaces with genus and boundaries.
• 

  Discrete Laplacians for Polygons and Polyhedral

  Prof.Mario Botsch

  Mar 13, 10:15 - 11:15

  B4 L5 R5209

  discrete laplacians polygons polyhedra computer graphics

  Being able to accurately solve PDEs on arbitrary polygonal/polyhedral meshes is a central goal and has been considered for various differential operators over the last years. In this talk I will present a simple approach for computing (piecewise) linear and quadratic basis functions for general polygons and polyhedra, from which discrete operators for gradient, divergence and Laplacian can be derived.
• 

  5-axis flank CNC machining of free-form surfaces using custom-shaped tools

  Dr.Michael Barton

  Mar 13, 09:00 - 10:00

  B4 L5 R5209

  free-form surfaces geometric computing

  In this talk, I will discuss our recent advances in approximation of free-form surfaces by motions of curvature varying tools in the context of 5-axis flank CNC machining. In particular, I will discuss path-planning strategies using fixed tools, or custom-shaped ones, and on an example of spiral bevel gears will demonstrate even more efficient variant of flank machining, called double-flank.
• 

  Workshop on Applied Geometry and Visual Computing

  Mar 13, 08:55 - 17:00

  B4 L5 R5209

  applied geometry visual computing discrete differential geometry geometry processing

  The “KAUST Workshop on Applied Geometry and Visual Computing” brings together leading scientists from Europe and the United States, presenting their latest results in - Applied and Discrete Differential Geometry - Geometry Processing - Computational Fabrication The talks are related to various problems in Applied Mathematics in general and to further areas of Visual Computing such as Computer Graphics, Physical Simulation and Scientific Visualization. The workshop provides a great opportunity to learn about latest developments and to discuss ongoing work with top researchers in the field.

Mar 5 - Mar 11, 2023

• 

  An Overview of Systems Research at TU Munich

  Pramod Bhatotia, Chair Professor, Department of Computer Science, the Technical University of Munich (TUM), Germany.

  Mar 9, 15:30 - 16:30

  B4 L5 R5209

  distributed systems operating systems

  In this talk, Professor Pramod Bhatotia will give an overview of systems research at TU Munich. He will cover his teaching and ongoing research projects. And will conclude the talk with a brief overview of his ERC project.
• 

  A Data Science Pipeline for Big Linked Earth Observation Data

  Prof.Manolis Koubarakis, Informatics and Telecommunications, National and Kapodistrian University of Athens

  Mar 6, 12:00 - 13:00

  B9 L2 H2 H2

  pipeline Geospatial Data GeoSPARQL

  I will present a data science pipeline which starts with Earth observation data arriving in the ground segment of a satellite mission and ends with a complete user application. I will first briefly present all the tools my group has been developing since 2010 for supporting the various stages of the pipeline. Then, I will concentrate on the recently developed system Strabo 2 which can store big geospatial data encoded in RDF and query them using the Open Geospatial Consortium standard GeoSPARQL. Strabo 2 is the only parallel and distributed RDF store available today that can manage terabytes of geospatial data efficiently.

Feb 26 - Mar 4, 2023

• 

  Controlling acoustic wave propagation via rotational motion

  Ying Wu, Professor, Applied Mathematics and Computational Sciences

  Feb 27, 12:00 - 13:00

  B9 L2 H2 H2

  acoustic waves

  Propagation of acoustic waves in time-varying and/or moving media has attracted a lot of attentions and is expected to lead to many intriguing applications. In this talk, I will discuss our recent work on acoustic wave propagation in spinning media (air or water). I will start with a review of the theoretical foundation built upon the Mie scattering framework, in which both the wave equation and the boundary conditions will be specifically discussed. The study is limited in the linear regime and exhibit the peculiar scattering features.
• 

  Learned Optics — Improving Computational Imaging Systems through Deep Learning and Optimization

  Wolfgang Heidrich, Professor, Computer Science

  Feb 26, 12:00 - 13:00

  B9 L2 H2

  Learned Optics

  Computational imaging systems are based on the joint design of optics and associated image reconstruction algorithms.

Feb 19 - Feb 25, 2023

• 

  Visualization Methods for Graphs&Networks

  Prof.Oliver Deussen, Visual Computing, University of Konstanz

  Feb 20, 12:00 - 13:00

  B9 L2 H2 H2

  visualization force-directed layouts stress-based methods vector-based constraints

  Inevitably, the projection of most graph structures on two-dimensional screens will create errors and therefore visually wrong impressions. In the past, two types of methods have been developed to minimize projection errors and distribute them in a visually pleasing way. The first group of methods, force-directed layouts, interpret the links of a graph as physical springs, while stress-based methods minimize an energy function, which aims to map graph distances faithfully.

Feb 12 - Feb 18, 2023

• 

  Generative Models for Neural Fields

  Ivan Skorokhodov, Ph.D. Student, Computer Science

  Feb 15, 20:10 - 22:00

  B1 L2 R2202

  Deep generative models

  In computer vision, generative AI models are typically built for images, videos, and 3D objects. Recently, there has emerged a paradigm of neural fields, which unifies the representations of such types of data by parametrizing them via neural networks. In this thesis, we develop generative models for images, videos, and 3D scenes which treat the underlying data in such a form and explore the benefits which such a perspective provides.
• 

  Extracting Semantic and Geometric Information in Images and Videos using GANs

  Rameen Abdal, Ph.D. Student, Computer Science

  Feb 15, 18:00 - 20:00

  B1 L2 R2202

  GaN

  The success of Generative Adversarial Networks (GANs) has resulted in unprecedented quality both for image generation and manipulation. Recent state-of-the-art GANs (e.g., the StyleGAN series) have demonstrated outstanding results in photo-realistic image generation. In this dissertation, we explore the latent space properties, including image manipulation, extraction of 3D properties, and performing various weakly supervised and unsupervised downstream tasks using StyleGAN and its derivative architectures.
• 

  Entrepreneurship Explored

  Prof.Bülent Erbilgin and Dr.Lama Hakem, KAUST Entrepreneurship Center

  Feb 13, 12:00 - 13:00

  B9 L2 H2 H2

  entrepreneurship Market marketing

  Entrepreneurs continue to be the driver for economic development and innovation. Some startups invent brand new markets while other manage to enter markets crowded by existing large companies. In this seminar we will explore making critical early decisions starting from chaos and creating an exciting new business. We will gain insights on the value of learning by doing, prototyping, discussing tradeoffs between analysis, experimentation and scale. We will also review courses offered by KAUST Entrepreneurship Center.
• 

  Designing, Synthesizing, and Automating Domain-Specific Accelerators

  Jian Weng, PhD student, Computer Science Department, UCLA

  Feb 12, 08:30 - 09:30

  KAUST

  Digital signal processing

  In this talk, I will first discuss how my research democratizes the accelerator designs and unifies the hardware/software innovations by automating the accelerator design process under a unified programming paradigm. By taking advantage of the compiler’s awareness of the program behaviors that profit from hardware specialization, accelerators can be automatically synthesized by searching through a well-defined design space. These automatically designed accelerators achieve comparable cost/performance efficiency compared with prior handcrafted designs. In the rest of the talk, I will also cover how this work inspires me to develop techniques to accelerate emerging application domains by orders-of-magnitude speedup, including digital signal processing and DNN inference, and how I take advantage of this work to revolutionize the FPGA programming paradigm.

Feb 5 - Feb 11, 2023

• 

  Vulnerability discovery in binaries and protocols

  Prof. Sven Dietrich, the Computer Science Department, Hunter College, the City University of New York (CUNY)

  Feb 9, 15:30 - 16:30

  B5 L5 R5209

  software

  Vulnerability discovery can be challenging: many software packages, both open and closed-source projects, build on existing code from public software repositories to network drives, derived from earlier versions or related software packages. Even implemented protocols rely on such repositories. It is important to detect such copies of code when the original code contains a software vulnerability, especially one that is exploitable, as seen with flaws such as the bash vulnerability Shellshock or the SSL vulnerability Heartbleed.
• 

  Point processes and their application to modeling drug seizure and overdose interactions

  Prof. George Mohler, Computer Science, Boston College

  Feb 8, 17:00 - 18:00

  KAUST

  point processes stochastic models

  In this talk we first provide an introduction to point processes, which are stochastic models for the occurrence of events in space and time. We then discuss the application of point processes to investigate the relationship between law enforcement drug seizures and accidental overdoses in Indianapolis. We will also discuss results from a field-experiment in Indianapolis where point process based harm indices were used to inform the distribution of addiction treatment information.
• 

  Machine-learning-assisted Quality of Transmission Estimation in Optical Networks

  Andrea Bianco, Full Professor, Electronics and Telecommunications Department at Politecnico di Torino

  Feb 8, 13:00 - 14:00

  B9 L4 R4125

  machine learning explainable AI framework artificial intelligence

  Machine Learning (ML) tools have recently been adopted for a wide range of automated operations in optical networking, moving fundamental steps towards the paradigm of zero-touch infrastructures. One example of such tasks is estimating the Quality of transmission of a lightpath prior to its establishment, which is particularly challenging due to the non-linear characteristics of signal propagation in optical fibers and to the often-incomplete knowledge of equipment parameters. This talk provides an overview of the contribution of my research team in the field of ML-based lightpath QoT estimation, including transfer learning approaches for inter-domain model adaptation, active learning for model building with small-sized training dataset, quantification of prediction uncertainty, and adoption of Explainable AI framework to expose the internal decisional mechanisms of trained models.
• 

  EF21-P and friends: Improved theoretical communication complexity for distributed optimization with bidirectional compression

  Feb 6, 12:00 - 13:00

  B9 L2 H2 H2

  EF21-P distributed optimization gradient descent operation

  In this work we focus our attention on distributed optimization problems in the context where the communication time between the server and the workers is non-negligible. We obtain novel methods supporting bidirectional compression (both from the server to the workers and vice versa) that enjoy new state-of-the-art theoretical communication complexity for convex and nonconvex problems.

Jan 29 - Feb 4, 2023

• 

  Fighting against cyber threats from a system perspective

  Prof. David Bromberg, Distributed computing systems, University of Rennes (IRISA)

  Feb 2, 15:30 - 16:30

  B4 L5 R5220.

  cyber threats

  In this talk we will explore how research in systems and distributed systems may improve the resilience to cyber attacks following 3 axes targeting mobile systems, distributed systems, and operating systems
• 

  Prototypical Random Walk Learning Mechanisms for Few-shot Learning, Novel Visual Generation, and (Continual)? Zero-shot Recognition

  Mohamed Elhoseiny, Associate Professor, Computer Science

  Jan 30, 12:00 - 13:00

  B9 L2 H2 H2

  prototypical random walks zero-shot recognition

  In this talk, we will define prototypical random walks, a mechanism we introduced to improve visual classification with limited data (few-shot learning), and then developed the mechanism in a conceptually different way to facilitate novel image generation and unseen class recognition tasks. More specifically, in the few-shot learning setting, we will show how we can develop a random walk semi-supervised loss that enables the network to learn representations that are compact and well-separated.

Jan 22 - Jan 28, 2023

• 

  Securing data against non-conventional adversaries

  Prof. Mohammad Mannan, Concordia Institute for Information Systems Engineering, Concordia University, Montreal

  Jan 26, 15:30 - 16:30

  B4 L5 R5220.

  data security

  I will discuss four related proposals: Gracewipe (coercion-resistant disk data deletion), Hypnoguard (cold-boot protection for RAM data in sleep), SafeKeeper (protecting web credentials from rougue IT admins), and Blindfold (protecting PKI private keys from human admins). While our solutions are possibly a step forward, more importantly, we highlight pitfalls of such solutions against a strong adversary.
• 

  Towards Richer Video Representation for Action Understanding

  Humam Alwassel, Ph.D., Computer Science

  Jan 23, 18:30 - 20:30

  B2 L5 R5209

  Computer Vision machine learning Human Activity Recognition

  With video data dominating the internet traffic, it is crucial to develop automated models that can analyze and understand what humans do in videos. Such models must solve tasks such as action classification, temporal activity localization, spatiotemporal action detection, and video captioning. This dissertation aims to identify the challenges hindering the progress in human action understanding and propose novel solutions to overcome these challenges.
• 

  Principles and practice of TEE replication (and beyond)

  Prof.Rodrigo Rodrigues, Instituto Superior Tecnico (ULisboa)

  Jan 23, 12:00 - 13:00

  B9 L2 R2322 H1

  TEE replication TEEMS CFT replication protocol

  Trusted Execution Environments (TEEs) ensure the confidentiality and integrity of computations in hardware. Subject to the TEE's threat model, the hardware shields a computation from most externally induced fault behavior except crashes. As a result, a crash-fault tolerant (CFT) replication protocol should be sufficient when replicating trusted code inside TEEs. However, TEEs do not provide efficient and general means of ensuring the freshness of the external, persistent state. Therefore, CFT replication is insufficient for TEE computations with an external state, as this state could be rolled back to an earlier version when a TEE restarts. Furthermore, using BFT protocols in this setting is too conservative, because these protocols are designed to tolerate arbitrary behavior, not just rollback during a restart.