SOURCE-LINKED INTELLIGENCE

FreqDoor: A Hidden Trojan in the Frequency Domain for Backdoor Attacks on Vision-Language Models

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Vision-language models (VLMs) have recently shown excellent progress in open-ended image-to-text generation. However, their multimodal nature makes them persistently vulnerable to backdoor attacks. Existing backdoor triggers for VLMs are either spatial, textual, or bimodal, which may yield localized or recognizable trigger patterns. In this work, we explore a different attack surface and propose \ textsc {FreqDoor}, a training-time backdoor attack that implants triggers in the frequency domain. \ textsc {FreqDoor} mixes amplitude-spectrum components from a trigger-source image selectively whil

Read original source ↗ Open in workspace

recordType

paper

region

Global