BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks 事件

BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks arXiv:2606.02947v1 Announce Type: cross Abstract: Supervised fine-tuning is the predominant approach for adapting autoregressive vision-language models to downstream tasks. Recent work has shown that this paradigm is highly vulnerable to backdoor attacks, and that existing defenses are ineffective in open-ended generation settings. In response, we propose BYORn, a backdoor-robust fine-tuning fram