SciGuard is proposed, an agent-based guardrail that employs large language models, tools and external knowledge to assess and control risks in scientific AI interactions, and achieves a state-of-the-art harmlessness score on red-teaming queries, while maintaining high performance on benign tasks, without sacrificing sc...
Jiyan He, Hao-Xiang Guan, Weitao Feng et al.· AI for Science· 26 citations· ⚡4
Experimental results demonstrate that ReAgent effectively identifies inconsistencies between reported research findings and their supporting repository evidence, enabling transparent evidence traceability.
Qiu-Hong Shen, Ben-Long Wu, Han-Jin Liu et al.· 0 citations
SB is proposed, a structured, query-efficient jailbreak framework for T2V models that harnesses temporal consistency by encoding harmful intent as the transition between two individually harmless boundary states and proves that structured search facilitates effective vulnerability discovery under constrained query budg...
Xingkai Peng, Jun Jiang, Jia-Yang Liu et al.· arXiv.org· 0 citations
This work studies the channel delivering search and page observations is a fragile security boundary and introduces Authority-Chain Hijack (ACH), an expert-refined strategy that turns isolated search-result and page-content manipulations into a coherent evidence chain across seemingly corroborating sources.
Xuebin Li, Han-Qing Zhao, Si-Yuan Liang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
