Changjiang Li
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2NLP×2AI×1
Frequent co-authors
Research Timeline
2026
ACIArena: Toward Unified Evaluation for Agent Cascading Injection
The paper introduces ACIArena, a unified and comprehensive evaluation framework designed to systematically test the robustness of Multi-Agent Systems against complex Agent Cascading Injection attacks.
Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
The paper proposes a novel method to inject reliable, sustained backdoors into LLMs by compiling an activation steering vector into model weights, ensuring the backdoor only activates upon a specific trigger.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.CLRecentApr 14, 2026
Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
Rui Yin, Tianxu Han, Naen Xu, Changjiang Li +7 more
The paper proposes a novel method to inject reliable, sustained backdoors into LLMs by compiling an activation steering vector into model weights, ensuring the backdoor only activates upon a specific…
View →
cs.AIcs.CLcs.CRRecentApr 9, 2026