https://tau-ac-il.zoom.us/j/85063969240?pwd=t2xMC9bTXyQ2mtCTfTkywVCGJ8SvFc.1
Meeting ID: 850 6396 9240
Passcode: 529492

Electrical Engineering Systems Seminar

Speaker: Sol Yarkoni

M.Sc. student under the supervision of Prof. Roi Livni

Wednesday, 18^th June 2025, at 15:00

Low-Resource Reconstruction of Template-Memorized Images — Attack against Diffusion Models
Abstract

Diffusion models trained on large-scale datasets such as LAION have become foundational to modern generative AI. However, their reliance on uncurated web data introduces serious privacy risks, particularly through the unintended extraction of training images. This seminar presents the findings of the research paper “Low Resource Reconstruction Attacks Through Benign Prompts”, recently submitted to NeurIPS and an ICML workshop.

The talk introduces a low-resource image reconstruction attack capable of extracting template-memorized content from diffusion models using only black-box access and natural English prompts such as “Abstract Art T-Shirt.” The attack successfully reconstructs training images, including some containing real, identifiable individuals.

To contextualize the attack, the talk will also review the phenomenon of template memorization and examine how data scraped from e-commerce websites contributes to the image–text coupling hypothesized to underlie this behavior.

Sol Yarkoni is an M.Sc. student, experienced data scientist in computer vision, and generative artist.

השתתפות בסמינר תיתן קרדיט שמיעה = עפ"י רישום בצ'ט של שם מלא + מספר ת.ז.

הרישום לסמינר יבוצע באמצעות סריקת הברקוד למודל (יש להיכנס לפני כן למודל,  לא באמצעות האפליקציה)- הרישום מתחיל ב- 15:30 ומסתיים ב- 15:40

Registration to the seminar will be done by scanning the barcode for the Moodle (Please enter ahead to the Moodle, NOT by application)- Registration ends at 15:10

Electrical Engineering Systems Seminar

Speaker: Daniel Toma

M.Sc. student under the supervision of Dr. Wasim Huleihel

Sunday, 15th June 2025, at 15:30

Room 011, Kitot Building, Faculty of Engineering

Sequential Classification of Misinformation

In recent years there have been a growing interest in online auditing of information flow over social networks with the goal of monitoring undesirable effects, such as, misinformation and fake news. Most previous work on the subject, focus on the binary classification problem of classifying information as fake or genuine. Nonetheless, in many practical scenarios, the multi-class/label setting is of particular importance. For example, it could be the case that a social media platform may want to distinguish between ``true", ``partly-true", and ``false" information. Accordingly, in this thesis, we consider the problem of online multiclass classification of information flow. To that end, driven by empirical studies on information flow over real-world social media networks, we propose a probabilistic information flow model over graphs. Then, the learning task is to detect the label of the information flow, with the goal of minimizing a combination of the classification error and the detection time. For this problem, we propose two detection algorithms; the first is based on the well-known multiple sequential probability ratio test, while the second is a novel graph neural network based sequential decision algorithm. For both algorithms, we prove several strong statistical guarantees. We also construct a data driven algorithm for learning the proposed probabilistic model. Finally, we test our algorithms over two real-world datasets, and show that they outperform other state-of-the-art misinformation detection algorithms, in terms of detection time and classification error.

Assembling and Disassembling Solids using Collective Action

Monday August 4th 2025 at 14:00 

Wolfson Building of Mechanical Engineering, Room 206

Abstract:

Swarm robotics is a promising methodology for accomplishing complicated tasks through the collective behavior of multiple active units. Interactions between active individuals in animal collectives (like fire ants and worms) lead to emergent responses that remain elusive in synthetic systems. In this talk, I present shape-morphing polymers as a framework to create bio-inspired transient swarms that can self-assemble into a stable solid structure, modulate their mechanical properties, and disassemble on demand. The solids are composed of aggregates of many magnetic, heat-responsive liquid crystal elastomer ribbons. Dilute-suspensions of curved and moving ribbons mechanically interlock, inducing reversible aggregation. The degree of bend and twist of the ribbon and the motion of the ribbon in a rotating external field control how ribbons interact with one another. A mathematical model is developed that sheds light on the role of topological mechanisms in aggregation. The ribbon suspensions reversibly transition between fluid- and solid-like states, exhibiting up to 6 orders-of-magnitude increase in the storage moduli of the entangled aggregates compared with the liquid dispersions. Subsequent heating resulted in a 2-fold increase in both stiffness and yield stress. Controlled dissociation is induced by imparting kinetic energy to the individual ribbons at high magnetic field rotation speeds. Study results provide insights that can lead to advancements in control and task programming of such swarming systems, specifically, by designing mechanical and chemo-mechanical switches for system manipulation. Imparting dynamic collective behaviors into synthetic systems may enable a range of potential applications from autonomous bio-inspired soft robotics to injectable biomaterials.

Bio:

Dr. Asaf Dana is an incoming assistant professor in the Department of Mechanical and Materials Engineering at the University of Nebraska – Lincoln. Until recently, he was a postdoctoral researcher in the Departments of Biomedical Engineering and Materials Science and Engineering at Texas A&M University. His current research focuses on developing soft stimuli-responsive material platforms for applications in tissue engineering, soft robotics and materials processing. Dr. Dana received his Ph.D. (2022) from the Department of Mechanical Engineering at the Technion – Israel Institute of Technology, focusing on the design of a previously unaccessed high-rate actuation mode of shape memory alloys. His research interests include the mechanics of responsive materials with emphasis on processes involving phase transitions in fabrication and actuation. In his research, he develops new experimental systems and methods to study the fundamental relations between microstructural evolution and macro-scale response and employs this knowledge for the development of new engineering design tools for smart and responsive systems.