DropVLA is presented, an action-level backdoor attack that forces a reusable action primitive to execute at attacker-chosen decision points under a realistic pipeline-black-box setting with limited data-poisoning access, using a window-consistent relabeling scheme for chunked fine-tuning.
Zong-Huan Xu, Jiayu Li, Yun-Han Zhao et al.· 5 citations
WithEveryone, a unified framework for generating group images up to ten reference identities, is introduced, showing that explicit identity--layout grounding enables identity-preserving generation to scale to larger groups without relying on direct reference-face copying.
Heng-Yuan Xu, Qixun Wang, Yiji Cheng et al.· 0 citations
This work proposes the Evolutionary Markov Hypergraph Attack (EMHA), a black-box policy that performs feedback-driven environment evolution by coordinating authorized state transitions without requiring parameter updates, and establishes OpenART as a scalable foundation for studying agent safety in complex, evolving en...
Yunhao Chen, Xin Wang, Yi-Xu Wang 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.