Image-generation models can now produce text-rich, natural-looking visual artifacts that are hard to distinguish from real-world evidence, such as news reports and textbook pages. Yet, the same capability introduces a new risk: these models can just as easily fabricate visual misinformation. Even commercial models (e.g...
Ze-Yu Ye, Yan-Chun Li, Si-Bei He et al.· 1 citation
This work proposes ReGap, a data-free attack that recovers private associations using task structure, filters them by answer-token likelihood, and updates the target model via low-rank adaptation, which requires neither target answers nor auxiliary genuine private supervision.
Jian-Hong Li, Jia-Hao Chen, Yuwen Pu et al.· 0 citations
SAVER is introduced, a transition-centered framework in which Substrate locates reusable influence, Adaptation captures how it changes, Violation identifies compromised safety attributes, Exposure marks where failures become observable, and Response assesses containment, repair, or revocation.
Jia-Hao Chen, Zhou Feng, Ou-Bo Ma et al.· 1 citation
JevAdvBench is introduced, to the authors' knowledge the first adversarial benchmark for RLCD models, with 812 typed questions over 66 scenarios, and a black-box attack suite of 9,744 single-edit variants that each edit one part of a request, with billed input tokens confirming that the edit reached the model.
Jian-Yi Hu, Hang Zhang, Yi Liu et al.· arXiv.org· 22 citations· ⚡4
ODPure is proposed, a novel input-stage black-box defense for object detection, which is based on input purification that ensures stable perception flows and provides robust defense against diverse backdoor attacks and trigger types while preserving baseline accuracy.
Li Zeng, Ming-Cheng Duan, Long-Fei Fan et al.· 0 citations
This paper introduces the concept of instruction-dense visual jailbreaks, in which image-generation models produce detailed, readable, and actionable harmful instructions within images, and proposes TYPO, a black-box framework that exploits this safety gap by automatically generating adversarial TYPOgraphy prompts.
Meng Xie, Li Zeng, Hang Zhang et al.· arXiv.org· 0 citations
Vision-Language Models (VLMs) are known to be vulnerable to adversarial attacks, where subtle perturbations to images or texts induce erroneous outputs. However, most text-based attacks are adapted from language-model-centric methods, in which the visual input is fixed during optimization, resulting in adversarial prom...
Li Zeng, Ze-Yu Ye, Meng Xie et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.