Addad, Boussad
- DiffGuard: Text-Based Safety Checker for Diffusion Models
2024/11/25 by M. Khader, Elias Al Bouzidi, Khader, Massine El +15 · 2 citations
Computer Science · #Software Reliability and Analysis Research #Formal Methods in Verification #Model-Driven Software Engineering Techniques
- Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models
2025/03/08 by Winninger, Thomas, Addad, Boussad, Kapusta, Katarzyna · 3 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)