arXiv Machine Learning

What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks

arXiv:2606. 09700v1 Announce Type: cross Abstract: Large language model (LLM)-powered content moderation systems have become a critical defense against harmful online content.

Hugging Face Trending Papers
Jul 7

AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models

Text-to-image diffusion models have achieved high visual fidelity and broad adoption, but remain vulnerable to safety violations when adversaries exploit them to synthesize illicit content. Existing alignment paradigms, from input sanitization to structural feature pruning, are largely organized around unsafe concepts explicitly exposed during filtering, editing, or localization.

arXiv AI
Jun 10

Attacks on Machine-Text Detectors Retain Stylistic Fingerprints

arXiv:2505. 14608v3 Announce Type: replace-cross Abstract: Despite considerable progress in the development of machine-text detectors, the ease with which machine-text can be manipulated to evade detection has led to suggestions that the problem is inherently intractable.

By Rafael Rivera Soto, Barry Chen, Nicholas Andrews
arXiv AI
Jul 21

Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models

arXiv:2607. 17779v1 Announce Type: new Abstract: Text-to-Image (T2I) generative models have achieved remarkable progress in synthesizing high-quality visual content, yet they remain vulnerable to adversarial misuse, particularly in generating Not-Safe-For-Work (NSFW) images.

By Dongdong Yang, Deyue Zhang, Zhao Liu, Zonghao Ying, Wenzhuo Xu, Jiankai Jin, Xiangzheng Zhang, Quanchen Zou
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