Scholar
Katarzyna Kapusta
Google Scholar ID: 8siuNBAAAAAJ
Thales ThereSIS
AI security
privacy-preserving ML
data protection
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
347
H-index
9
i10-index
9
Publications
20
Co-authors
0
Publications
3 items
Breaking the weakest link to evade vision language models
2026
Cited
0
Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models
2025
Cited
0
DiffGuard: Text-Based Safety Checker for Diffusion Models
arXiv.org · 2024
Cited
0
