DF-LoGiT: 视觉变换器中的无数据逻辑门后门攻击
DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers
AI总结：
DF-LoGiT提出了一种无需数据的视觉变换器后门攻击方法，通过直接修改权重实现隐蔽且高效的后门植入。
摘要：
视觉变换器（ViTs）的广泛应用提高了第三方模型库中的供应链风险，其中攻击者可以将后门植入发布的检查点中。现有的ViT后门攻击大多依赖于毒化数据训练，而先前的无数据尝试通常需要合成数据微调或额外的模型组件。本文介绍了无数据逻辑门后门攻击（DF-LoGiT），通过直接权重编辑在ViTs上实现真正的无数据后门攻击。DF-LoGiT利用ViT的原生多头架构实现逻辑门组合触发器，从而实现隐蔽且有效的后门。我们通过理论分析和广泛的实验验证其有效性，显示DF-LoGiT在几乎100%的攻击成功率下，对良性准确率的降级影响极小，并且对代表性经典和ViT特定的防御措施保持稳健。
英文摘要：
The widespread adoption of Vision Transformers (ViTs) elevates supply-chain risk on third-party model hubs, where an adversary can implant backdoors into released checkpoints. Existing ViT backdoor attacks largely rely on poisoned-data training, while prior data-free attempts typically require synthetic-data fine-tuning or extra model components. This paper introduces Data-Free Logic-Gated Backdoor Attacks (DF-LoGiT), a truly data-free backdoor attack on ViTs via direct weight editing. DF-LoGiT exploits ViT's native multi-head architecture to realize a logic-gated compositional trigger, enabling a stealthy and effective backdoor. We validate its effectiveness through theoretical analysis and extensive experiments, showing that DF-LoGiT achieves near-100% attack success with negligible degradation in benign accuracy and remains robust against representative classical and ViT-specific defenses.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
