15 citations · 48 across the 19 of their papers we have counts for
20 papers
Through the LENS: Local Geometric Decomposition of Vision-Language Model Representations
Shalom Kachko, Raz Lapid, Margarita Vald +2
Vision-language models (VLMs) process image patches and text tokens in a shared residual stream, but the local geometry through which the two modalities interact remains poorly und…
Mirage Probes: How Vision Models Fake Visual Understanding
Daniel Ben-Levi, Judah Goldfeder, Weiliang Zhao +5
Vision-language models (VLMs) can answer image-based questions confidently, and often correctly, even when no image is provided. This mirage behavior inflates benchmark scores with…
On the Robustness of Diffusion-Based Image Compression to Bit-Flip Errors
Amit Vaisman, Gal Pomerants, Raz Lapid
Modern image compression methods are typically optimized for the rate--distortion--perception trade-off, whereas their robustness to bit-level corruption is rarely examined. We sho…
BenchOverflow: Measuring Overflow in Large Language Models via Plain-Text Prompts
Erin Feiglin, Nir Hutnik, Raz Lapid
We investigate a failure mode of large language models (LLMs) in which plain-text prompts elicit excessive outputs, a phenomenon we term Overflow. Unlike jailbreaks or prompt injec…
Breaking Audio Large Language Models by Attacking Only the Encoder: A Universal Targeted Latent-Space Audio Attack
Roee Ziv, Raz Lapid, Moshe Sipper
Audio-language models combine audio encoders with large language models to enable multimodal reasoning, but they also introduce new security vulnerabilities. We propose a universal…
Activation Steering for Masked Diffusion Language Models
Adi Shnaidman, Erin Feiglin, Osher Yaari +3
Masked diffusion language models (MDLMs) generate text via iterative masked-token denoising, enabling mask-parallel decoding and distinct controllability and efficiency tradeoffs f…
You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations
Amit LeVi, Raz Lapid, Rom Himelstein +3
Many LLM applications require only narrow capabilities, yet standard post-training quantization (PTQ) methods allocate precision without considering the target task. This can waste…
Backdoors in Conditional Diffusion: Threats to Responsible Synthetic Data Pipelines
Raz Lapid, Almog Dubin
Text-to-image diffusion models achieve high-fidelity image generation from natural language prompts. ControlNets extend these models by enabling conditioning on structural inputs (…
Don't Lag, RAG: Training-Free Adversarial Detection Using RAG
Roie Kazoom, Raz Lapid, Moshe Sipper +1
Adversarial patch attacks pose a major threat to vision systems by embedding localized perturbations that mislead deep models. Traditional defense methods often require retraining…
Pulling Back the Curtain: Unsupervised Adversarial Detection via Contrastive Auxiliary Networks
Eylon Mizrahi, Raz Lapid, Moshe Sipper
Deep learning models are widely employed in safety-critical applications yet remain susceptible to adversarial attacks -- imperceptible perturbations that can significantly degrade…
On the Robustness of Kolmogorov-Arnold Networks: An Adversarial Perspective
Tal Alter, Raz Lapid, Moshe Sipper
Kolmogorov-Arnold Networks (KANs) have recently emerged as a novel approach to function approximation, demonstrating remarkable potential in various domains. Despite their theoreti…
Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectors
Raz Lapid, Almog Dubin, Moshe Sipper
This paper presents RADAR-Robust Adversarial Detection via Adversarial Retraining-an approach designed to enhance the robustness of adversarial detectors against adaptive attacks,…
XAI-Based Detection of Adversarial Attacks on Deepfake Detectors
Ben Pinhasov, Raz Lapid, Rony Ohayon +2
We introduce a novel methodology for identifying adversarial attacks on deepfake detectors using eXplainable Artificial Intelligence (XAI). In an era characterized by digital advan…
Open Sesame! Universal Black Box Jailbreaking of Large Language Models
Raz Lapid, Ron Langberg, Moshe Sipper
Large language models (LLMs), designed to provide helpful and safe responses, often rely on alignment techniques to align with user intent and social guidelines. Unfortunately, thi…
I See Dead People: Gray-Box Adversarial Attack on Image-To-Text Models
Raz Lapid, Moshe Sipper
Modern image-to-text systems typically adopt the encoder-decoder framework, which comprises two main components: an image encoder, responsible for extracting image features, and a…
A Melting Pot of Evolution and Learning
Moshe Sipper, Achiya Elyasaf, Tomer Halperin +5
We survey eight recent works by our group, involving the successful blending of evolutionary algorithms with machine learning and deep learning: 1. Binary and Multinomial Classific…
Patch of Invisibility: Naturalistic Physical Black-Box Adversarial Attacks on Object Detectors
Raz Lapid, Eylon Mizrahi, Moshe Sipper
Adversarial attacks on deep learning models have received increased attention in recent years. Work in this area has mostly focused on gradient-based techniques, so-called 'white-b…
Foiling Explanations in Deep Neural Networks
Snir Vitrack Tamam, Raz Lapid, Moshe Sipper
Deep neural networks (DNNs) have greatly impacted numerous fields over the past decade. Yet despite exhibiting superb performance over many problems, their black-box nature still p…
An Evolutionary, Gradient-Free, Query-Efficient, Black-Box Algorithm for Generating Adversarial Instances in Deep Networks
Raz Lapid, Zvika Haramaty, Moshe Sipper
Deep neural networks (DNNs) are sensitive to adversarial data in a variety of scenarios, including the black-box scenario, where the attacker is only allowed to query the trained m…
Evolution of Activation Functions for Deep Learning-Based Image Classification
Raz Lapid, Moshe Sipper
Activation functions (AFs) play a pivotal role in the performance of neural networks. The Rectified Linear Unit (ReLU) is currently the most commonly used AF. Several replacements…