Jannatul Ferdaus
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1Crypto×1
Frequent co-authors
Research Timeline
2026
When Safety Geometry Collapses: Fine-Tuning Vulnerabilities in Agentic Guard Models
The paper demonstrates that fine-tuning safety guard models on benign data can catastrophically collapse their safety alignment, proposing Fisher-Weighted Safety Subspace Regularization (FW-SSR) to actively maintain safety geometry.
Highlighted terms show continued research focus across papers