LLM-based guardrails are effective against indirect prompt injection (IPI), but their performance depends heavily on model capability: as the guardrail model becomes smaller or weaker, detection degrades substantially. This raises a natural question: can we retain strong IPI defense while relying only on a small LLM? T...
Yin-Xiang Wang, Ze-Hua Ma, Ke-Jiang Chen et al.· 0 citations
Invisible image watermark removal has received growing attention. Despite substantial progress, existing attacks face a tension between practicality and specificity. Attacks exploiting detector outputs, decoder responses, or paired images can be tailored to the watermark decision boundary, but require information rarel...
Jun Yao, Chao Wang, Yu-Peng Qiu et al.· 0 citations
Dual-stage Native Attribution (DNA) is proposed, a coarse-to-fine framework that follows this hierarchy without additional neural-network training that achieves 89.11% end-to-end attribution accuracy on a task where random guessing accuracy is below 1% and outperforms the strongest baseline by 33.81% even when AEDR is...
Chao Wang, Ke-Jiang Chen, Zi-Jin Yang et al.· arXiv.org· 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
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
