Black-Box Behavioral Fingerprinting is proposed: the prompt owner registers a behavioral signature from model outputs and later tests whether a suspect deployment matches that signature more closely than an unrelated baseline, and requires only black-box API access.
Ling-Han Chen, Yu-Dong Gao, Ji-Yao Wang et al.· 5 citations
Backdoor attacks pose a serious threat to the secure deployment of text-to-image (T2I) diffusion models. Existing defenses typically detect backdoors from specific abnormal patterns in internal representations, which may limit their generalizability with the emergence of increasingly diverse attack mechanisms. In this...
Jun-Jian Li, Xiao-Long Liu, Peng Sun et al.· 1 citation
LLM agents now execute tasks end to end with permission to change real systems and increasingly orchestrate subagents that differ in capability and cost. Prior work treats the choice of subagent as an optimization problem. Yet the orchestrator makes this choice from the identities that subagents display, and an attacke...
Xu-Tao Mao, Rui Qian, Ling-Han Chen et al.· 1 citation
Results show that preserving already-correct work under unsupported accusation is a distinct safety challenge for long-lived agents, and introduces CAVE-Bench, a benchmark of 365 agentic tasks across six domains built around opaque tasks.
Xu-Tao Mao, Rui Qian, Long-Xiang Wang et al.· 0 citations
This work presents the first bit-flip attack on a VLA: a few gradient-selected flips reduce closed-loop success to $0\%$, while hundreds of random flips are harmless.
Yu-Dong Gao, Ling-Han Chen, Wenhan Wu et al.· 2 citations
Seed2GS is presented, which achieves the highest reported LERF-MASK accuracy without original reconstruction cameras or scene-specific representation training, and its key insight is to separate target identity from 3D coverage.
Zong-Jiang Ding, Yu-Dong Gao, Jia-Le Liu et al.· 0 citations
These findings reveal substantial hidden dependencies among seemingly independent API resellers, which can create a large potential blast radius, where a confidentiality or integrity failure along a common upstream path may affect users across multiple downstream resellers.
Zimo Ji, Xin Wei, Congying Xu 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.
