2 papers
cs.CR2026
PathMark: Protecting Intellectual Property of Mixture-of-Expert LLMs via Path Watermarks
Yudong Gao, Qingyue Wang, Yuanyuan Yuan +4
Mixture-of-Experts (MoE) large language models represent high-value intellectual property, yet existing watermarking schemes designed for dense models fail on MoE architectures due…
cs.LG2026
Attacking the Trusted Imagination: Oracle-Level Integrity Attacks on Imagine-then-Act World Models
Linghan Chen, Kaiyan Ji, Minyu Guo
Many recent vision-language-action (VLA) policies adopt an imagine-then-act design. A world-action model (WAM) first imagines a short future as a latent trajectory z~, on which the…