作者位次 #4/7CVPR 2026Poster· Computer Vision & Pattern Recognition
FORCE: Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEction
Runqi Lin · Alasdair Paren · Suqin Yuan · Muyang Li · Philip Torr · Adel Bibi · Tongliang Liu
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Runqi Lin · Alasdair Paren · Suqin Yuan · Muyang Li · Philip Torr · Adel Bibi · Tongliang Liu
Muyang Li · Yucheng Liu · Jianbo Ma · Elliot Osborne · Bo Han · Tongliang Liu
Muyang Li · Runze Wu · an Jiaotong University) · Bo Han · Daoyi Dong · Tongliang Liu
The post-training stage of Large Language Models (LLMs) typically involves Supervised Fine-Tuning (SFT) followed by preference alignment to ensure LLM to generate safe, helpful, and instruction-aligned content. The SFT model critically serves as both the initialization and reference model for sub...