2 citations · 4 across the 10 of their papers we have counts for
12 papers
BadEngram: Backdoor Attack on Gated Memory Components in LLMs
Ariel Fogel, Omer Hofman, Eilon Cohen +1
To expand open-weight models' capacity without proportionally increasing computation, recent architectures incorporate gated parametric memory that retrieves learned values and inj…
An Actionable Diagnosis of Multilingual, Multi-Agent Planning Failures
Vikas Pahuja, Jonathan Brokman, Omer Hofman +6
Multilingual multi-agent systems exhibit substantial degradation beyond English, yet prior work rarely identifies how task-critical information is lost when user requests are conve…
When Scanners Lie: Evaluator Instability in LLM Red-Teaming
Lidor Erez, Omer Hofman, Tamir Nizri +1
Automated LLM vulnerability scanners are increasingly used to assess security risks by measuring different attack type success rates (ASR). Yet the validity of these measurements h…
Inference-Time Backdoors via Chat Templates: From LLM Supply Chains to Agentic System Compromise
Ariel Fogel, Omer Hofman, Eilon Cohen +1
Open-weight language models are increasingly used in production settings, raising new security challenges. One prominent threat is backdoor attacks, in which adversaries embed hidd…
General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood
Roy Betser, Omer Hofman, Roman Vainshtein +1
The rapid advancement of generative models, particularly diffusion-based methods, has significantly improved the realism of synthetic images. As new generative models continuously…
Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs
Oren Rachmil, Avishag Shapira, Roy Betser +5
As organizations increasingly deploy LLMs in sensitive domains such as legal, financial, and medical settings, ensuring alignment with internal organizational policies has become a…
MAPS: A Multilingual Benchmark for Agent Performance and Security
Omer Hofman, Jonathan Brokman, Oren Rachmil +7
Agentic AI systems, which build on Large Language Models (LLMs) and interact with tools and memory, have rapidly advanced in capability and scope. Yet, since LLMs have been shown t…
Identifying Memorization of Diffusion Models through -Laplace Analysis: Estimators, Bounds and Applications
Jonathan Brokman, Itay Gershon, Amit Giloni +4
Diffusion models, today's leading image generative models, estimate the score function, i.e. the gradient of the log probability of (perturbed) data samples, without direct access…
Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Images
Jonathan Brokman, Amit Giloni, Omer Hofman +3
Distinguishing between real and AI-generated images, commonly referred to as 'image detection', presents a timely and significant challenge. Despite extensive research in the (semi…
Insights and Current Gaps in Open-Source LLM Vulnerability Scanners: A Comparative Analysis
Jonathan Brokman, Omer Hofman, Oren Rachmil +6
This report presents a comparative analysis of open-source vulnerability scanners for conversational large language models (LLMs). As LLMs become integral to various applications,…
DIESEL -- Dynamic Inference-Guidance via Evasion of Semantic Embeddings in LLMs
Ben Ganon, Alon Zolfi, Omer Hofman +4
In recent years, large language models (LLMs) have had great success in tasks such as casual conversation, contributing to significant advancements in domains like virtual assistan…
X-Detect: Explainable Adversarial Patch Detection for Object Detectors in Retail
Omer Hofman, Amit Giloni, Yarin Hayun +4
Object detection models, which are widely used in various domains (such as retail), have been shown to be vulnerable to adversarial attacks. Existing methods for detecting adversar…