نسخة أولية وصول مفتوح
Purifying Backdoored Large Vision-Language Models by Removing Hijacked Directions
Large vision-language models (LVLMs) are increasingly deployed in safety-critical applications, yet they remain vulnerable to backdoor attacks. Defending against such attacks remains costly, as existing methods require either extensive retraining on clean data or per-query intervention at inference time. To address thi …