Chhavi Yadav
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1Crypto×1
Frequent co-authors
Research Timeline
2026
Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks
This paper demonstrates that existing open-weight LLM safeguards are vulnerable to simple, non-gradient-based attacks like abliteration and prefilling, significantly increasing the attack success rate.
Highlighted terms show continued research focus across papers