1.5k citations · 2.4k across the 38 of their papers we have counts for
43 papers
Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering Attacks
Guy Frankovits, Lior Yasur, Fred M. Grabovski +1
This paper presents DF-CAPTCHA, an active defense against real-time deepfake impersonation in voice and video calls. Instead of passively searching for artifacts, DF-CAPTCHA prompt…
Detokenization Leaks: Reconstructing Local LLM Outputs From Cache Traces
Roy Weiss, Benyamin Konstantinov, Eitam Sheetrit +2
We present a new attack that reconstructs the text generated by locally hosted LLMs by observing CPU cache activity during detokenization. Unlike prior attacks that rely on deploym…
Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents
Or Zion Eliav, Eyal Lenga, Shir Bernstien +1
Traditional pentesting uses reconnaissance at each step to uncover unseen weaknesses, build stronger attacks, and advance the objective; we argue that AI agents require the same tr…
PRISM: Recovering Instruction Sets from Language Model Activations
Gilad Gressel, Rahul Pankajakshan, Julia Diament +3
As LLMs are deployed as agents, reliable monitoring requires knowing not only what they output, but which instructions are steering their behavior. This is difficult when models in…
A Few Steps Further: Why Defenses Against Malicious Finetuning Erode Under Continued Training
Itay Zloczower, Eyal Lenga, Gilad Gressel +1
Model providers increasingly release the weights of large language models. Although these models are safety-aligned before release, their safeguards can often be removed by fine-tu…
Who Owns This Agent? Tracing AI Agents Back to Their Owners
Ruben Chocron, Doron Jonathan Ben Chayim, Eyal Lenga +3
AI agents increasingly act autonomously in the world, yet harmful behavior cannot be reliably traced to the account that deployed the agent. This creates an accountability gap acro…
LeakBoost: Perceptual-Loss-Based Membership Inference Attack
Amit Kravchik Taub, Fred M. Grabovski, Guy Amit +1
Membership inference attacks (MIAs) aim to determine whether a sample was part of a model's training set, posing serious privacy risks for modern machine-learning systems. Existing…
GAVEL: Towards Rule-Based Safety Through Activation Monitoring
Shir Rozenfeld, Rahul Pankajakshan, Itay Zloczower +3
Large language models (LLMs) are increasingly paired with activation-based monitoring to detect and prevent harmful behaviors that may not be apparent at the surface-text level. Ho…
Love, Lies, and Language Models: Investigating AI's Role in Romance-Baiting Scams
Gilad Gressel, Rahul Pankajakshan, Shir Rozenfeld +4
Romance-baiting scams have become a major source of financial and emotional harm worldwide. These operations are run by organized crime syndicates that traffic thousands of people…
ProxyPrints: From Database Breach to Spoof, A Plug-and-Play Defense for Biometric Systems
Yaniv Hacmon, Keren Gorelik, Gilad Gressel +1
Fingerprint recognition systems are widely deployed for authentication and forensic applications, but the security of stored fingerprint data remains a critical vulnerability. Whil…
Trust Me, I Know This Function: Hijacking LLM Static Analysis using Bias
Shir Bernstein, David Beste, Daniel Ayzenshteyn +2
Large Language Models (LLMs) are increasingly trusted to perform automated code review and static analysis at scale, supporting tasks such as vulnerability detection, summarization…
ASRJam: Human-Friendly AI Speech Jamming to Prevent Automated Phone Scams
Freddie Grabovski, Gilad Gressel, Yisroel Mirsky
Large Language Models (LLMs), combined with Text-to-Speech (TTS) and Automatic Speech Recognition (ASR), are increasingly used to automate voice phishing (vishing) scams. These sys…
PaniCar: Securing the Perception of Advanced Driving Assistance Systems Against Emergency Vehicle Lighting
Elad Feldman, Jacob Shams, Dudi Biton +7
The safety of autonomous cars has come under scrutiny in recent years, especially after 16 documented incidents involving Teslas (with autopilot engaged) crashing into parked emerg…
Memory Backdoor Attacks on Neural Networks
Eden Luzon, Guy Amit, Roy Weiss +3
Neural networks are often trained on proprietary datasets, making them attractive attack targets. We present a novel dataset extraction method leveraging an innovative training tim…
Efficient Model Extraction via Boundary Sampling
Maor Biton Dor, Yisroel Mirsky
This paper introduces a novel data-free model extraction attack that significantly advances the current state-of-the-art in terms of efficiency, accuracy, and effectiveness. Tradit…
PEAS: A Strategy for Crafting Transferable Adversarial Examples
Bar Avraham, Yisroel Mirsky
Black box attacks, where adversaries have limited knowledge of the target model, pose a significant threat to machine learning systems. Adversarial examples generated with a substi…
The Best Defense is a Good Offense: Countering LLM-Powered Cyberattacks
Daniel Ayzenshteyn, Roy Weiss, Yisroel Mirsky
As large language models (LLMs) continue to evolve, their potential use in automating cyberattacks becomes increasingly likely. With capabilities such as reconnaissance, exploitati…
Are You Human? An Adversarial Benchmark to Expose LLMs
Gilad Gressel, Rahul Pankajakshan, Yisroel Mirsky
Large Language Models (LLMs) have demonstrated an alarming ability to impersonate humans in conversation, raising concerns about their potential misuse in scams and deception. Huma…
Back-in-Time Diffusion: Unsupervised Detection of Medical Deepfakes
Fred Grabovski, Lior Yasur, Guy Amit +1
Recent progress in generative models has made it easier for a wide audience to edit and create image content, raising concerns about the proliferation of deepfakes, especially in h…
Counter-Samples: A Stateless Strategy to Neutralize Black Box Adversarial Attacks
Roey Bokobza, Yisroel Mirsky
Our paper presents a novel defence against black box attacks, where attackers use the victim model as an oracle to craft their adversarial examples. Unlike traditional preprocessin…
What Was Your Prompt? A Remote Keylogging Attack on AI Assistants
Roy Weiss, Daniel Ayzenshteyn, Guy Amit +1
AI assistants are becoming an integral part of society, used for asking advice or help in personal and confidential issues. In this paper, we unveil a novel side-channel that can b…
Transpose Attack: Stealing Datasets with Bidirectional Training
Guy Amit, Mosh Levy, Yisroel Mirsky
Deep neural networks are normally executed in the forward direction. However, in this work, we identify a vulnerability that enables models to be trained in both directions and on…
Discussion Paper: The Threat of Real Time Deepfakes
Guy Frankovits, Yisroel Mirsky
Generative deep learning models are able to create realistic audio and video. This technology has been used to impersonate the faces and voices of individuals. These ``deepfakes''…
Deepfake CAPTCHA: A Method for Preventing Fake Calls
Lior Yasur, Guy Frankovits, Fred M. Grabovski +1
Deep learning technology has made it possible to generate realistic content of specific individuals. These `deepfakes' can now be generated in real-time which enables attackers to…