Large language models (LLMs) deployed through text-only APIs face model extraction risks, as adversaries can collect their responses to train surrogates that reproduce their capabilities. While prior work has developed diverse attacks and defenses, evaluations remain fragmented across access assumptions, model configur...
Shu-Ze Liu, Kai-Xiang Zhao, Run-Yang Xu et al.· 0 citations
LLM compression reduces inference costs and memory requirements, but selecting a method and configuration remains largely empirical because comparable resource reductions can produce different capability losses. We systematically investigate capability scaling-down laws for LLM compression across pruning, quantization,...
Xue-Qi Cheng, Liang Wu, Kelly Wan et al.· 0 citations
Understanding and assessing natural hazards is essential for disaster preparedness and risk reduction. Recent advances in large language models have spurred growing interest in AI agents for hazard analysis, particularly their ability to integrate scientific data, models, and tools into automated workflows. However, ef...
Wang-Shu Zhu, Xue-Qi Cheng, Liang-Yu Wu et al.· 0 citations
How much does the noisy measurement add to learned quantum error mitigation? An accuracy table cannot say, because a model handed circuit structure can score well without reading the measurement at all. QEMScore adds the comparison that can. Each simulated circuit carries an exact ideal answer. The learned mitigator is...
Yue Zhao, Huayue Gu, Yu-Shun Dong et al.· 0 citations
Experiments show that Knowledge Trap reduces surrogate Agreement by 6.2\% on average without degrading legitimate-user accuracy, outperforming existing defenses that impose measurable user impact, and suggest that defending knowledge-space traversal is a practical direction for mitigating LLM extraction attacks.
This work forms model extraction monitoring as benign-calibrated traffic-window distribution testing: embed incoming queries into a semantic space and test whether their aggregate distribution deviates from historical benign traffic.
TIGER is presented, an inference-time framework that redesigns feedback for localized repair that reduces unsupported content while preserving task quality and a CrisisFACTS case study suggests that the same repair mechanism can improve grounding in multi-source settings.
Kaixiang Zhao, Tianrun Yu, Shawn Huang 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.
