Lei Li

TrajGuard is a novel, training-free defense framework that detects jailbreaks by monitoring the progressive risk signals embedded in the hidden-state trajectories of tokens during the LLM decoding process, achieving a high defense rate with low latency.

The paper proposes SemBugger, a polymorphic backdoor attack that uses intensity-based poisoning to achieve diverse malicious outcomes in Semantic Communication (SC) systems, alongside a provable defense mechanism.

The paper systematizes the interaction between autonomous AI agents and blockchain platforms using a bidirectional trust framework, identifying significant gaps in current standards and proposing a taxonomy for future research.

The paper introduces CORDON-MAS, a compartmentalized framework that defends Retrieval-Augmented Generation (RAG) against knowledge poisoning by enforcing strict information-flow control, significantly reducing attack success rates.

The paper introduces LongDS, a new benchmark for long-horizon, multi-turn data analysis, demonstrating that current AI agents struggle significantly with maintaining and updating complex analytical states over extended interactions.

The paper proposes a Signed Entropy Integral (SEI) statistic to detect mislabeled images in training datasets by analyzing the temporal trend of prediction entropy, achieving state-of-the-art results on medical imaging data.

SkillAdaptor is a novel, training-free framework that enables stable, step-level adaptation of external skills for LLM agents by precisely attributing failures to specific skills.

CRAFTQA introduces a novel adaptive, code-driven framework that significantly enhances complex structured data reasoning by dynamically generating custom code functions beyond predefined operations.

The paper introduces CRAB-Bench and RUSE, a rigorous evaluation framework that tests LLM agents on complex, interdependent tasks with realistic human user interactions, revealing significant performance gaps in current models.