6 papers
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…
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…
Adversarial Intent is a Latent Variable: Stateful Trust Inference for Securing Multimodal Agentic RAG
Inderjeet Singh, Vikas Pahuja, Aishvariya Priya Rathina Sabapathy +8
Current stateless defences for multimodal agentic RAG fail to detect adversarial strategies that distribute malicious semantics across retrieval, planning, and generation component…
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…
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…
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,…