Conference Intel
Best Talks Tools Rate My Talk About
Home / IEEE Symposium on Security and Privacy 2025 / Alleviating the Fear of Losing Alignment in LLM Fine-tuning

Alleviating the Fear of Losing Alignment in LLM Fine-tuning

Kang Yang, Guanhong Tao, Xun Chen, Jun Xu

IEEE Symposium on Security and Privacy 2025 · Day 2 · ML Defenses

← Fight Fire with Fire: Combating Adversarial Patch Attacks using… · On the Conflict between Robustness and Learning in Collaborative Machine… →

All talks from IEEE Symposium on Security and Privacy 2025

[ Conference Intel ]

Community-driven deep-dive coverage of leading security conferences.

Subscribe via RSS — new talk reviews as they publish.