DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shen, Xiaozuo, Cai, Yifei, Ning, Rui, Xin, Chunsheng, Wu, Hongyi
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908808052211712
author Shen, Xiaozuo
Cai, Yifei
Ning, Rui
Xin, Chunsheng
Wu, Hongyi
author_facet Shen, Xiaozuo
Cai, Yifei
Ning, Rui
Xin, Chunsheng
Wu, Hongyi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_03040
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers
Shen, Xiaozuo
Cai, Yifei
Ning, Rui
Xin, Chunsheng
Wu, Hongyi
Cryptography and Security
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.
title DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers
topic Cryptography and Security
url https://arxiv.org/abs/2602.03040