7 citations · 16 across the 11 of their papers we have counts for
11 papers
Breaking the weakest link to evade vision language models
Ilan Zini, Boussad Addad, Katarzyna Kapusta
Vision Language Models (VLMs) have recently emerged as a critical component of multimodal AI systems, enabling joint reasoning over visual and textual inputs in real-world and safe…
Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models
Thomas Winninger, Boussad Addad, Katarzyna Kapusta
Traditional white-box methods for creating adversarial perturbations against LLMs typically rely only on gradient computation from the targeted model, ignoring the internal mechani…
DiffGuard: Text-Based Safety Checker for Diffusion Models
Massine El Khader, Elias Al Bouzidi, Abdellah Oumida +6
Recent advances in Diffusion Models have enabled the generation of images from text, with powerful closed-source models like DALL-E and Midjourney leading the way. However, open-so…
When Federated Learning meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protection
Mohammed Lansari, Reda Bellafqira, Katarzyna Kapusta +3
Federated Learning (FL) is a technique that allows multiple participants to collaboratively train a Deep Neural Network (DNN) without the need of centralizing their data. Among oth…
Multi-hop Data Fragmentation in Unattended Wireless Sensor Networks
Keun-Woo Lim, Katarzyna Kapusta, Gerard Memmi +1
In this work, we analyze the advantages of multi-hop data fragmentation in unattended wireless sensor networks (UWSN) and propose a lightweight protocol to achieve it. UWSN has rec…
Revisiting Shared Data Protection Against Key Exposure
Katarzyna Kapusta, Gerard Memmi, Matthieu Rambaud
This paper puts a new light on secure data storage inside distributed systems. Specifically, it revisits computational secret sharing in a situation where the encryption key is exp…