# DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers Source: [DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers]() Collection index: [llms.txt]() Data updated: 2026-02-05T05:00:04.050Z Authors: Xiaozuo Shen, Yifei Cai, Rui Ning, Chunsheng Xin, Hongyi Wu Published: 2026-02-03T03:06:41.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on ImageNet-1K (test val) (Backdoor Attack Metrics)](): Image Classification; ImageNet 1k (test val); Clean Accuracy (C-ACC): not recorded. ## Original sources and implementation [Original paper]() [PDF]()