arXiv Machine Learning By Binyan Xu, Fan Yang, Di Tang, Xilin Dai, Kehuan Zhang

Breaking the Stealth-Potency Trade-off in Clean-Image Backdoors with Generative Trigger Optimization

Read the original on arXiv Machine Learning →

arXiv:2511. 07210v3 Announce Type: replace-cross Abstract: Clean-image backdoor attacks, which use only label manipulation in training datasets to compromise deep neural networks, pose a significant threat to security-critical applications.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
5d ago

Adjustable Text-Guided Backdoor Attacks with Natural-Word Triggers on Multimodal Pretrained Models

arXiv:2604. 05809v2 Announce Type: replace-cross Abstract: This paper presents Text-Guided Backdoor (TGB), an adjustable backdoor attack against multimodal pretrained models that uses natural-word triggers, namely words that can naturally occur in ordinary textual inputs.

By Yiyang Zhang, Chaojian Yu, Ziming Hong, Yuanjie Shao, Qinmu Peng, Tongliang Liu, Xinge You