Zhuo Li

Weaver is a novel greybox fuzzing framework designed to uncover security vulnerabilities at the complex interaction boundary between JavaScript and WebAssembly, achieving superior code coverage and finding high-severity bugs.

ClawKeeper is a comprehensive, multi-layered security framework designed to mitigate critical vulnerabilities in autonomous agent runtimes like OpenClaw by enforcing protection across skills, plugins, and system state.

TwinGate introduces a stateful dual-encoder defense framework using Asymmetric Contrastive Learning to detect malicious intent from fragmented, untraceable LLM queries with high recall and low false positives.

PropGuard introduces a propagation-aware framework to safeguard LLM-MAS against malicious attacks by constructing a dual-view graph, identifying suspicious propagation paths, and applying source-guided remediation.

The EvoSafety framework enhances LLM safety by externalizing attack and defense mechanisms, enabling persistent, transferable, and model-agnostic robustness against adversarial prompts.

Evo-Attacker introduces a memory-augmented reinforcement learning framework to perform generalized, long-horizon tool attacks on LLM-MAS, significantly outperforming existing methods.

The paper introduces Canonical-Context On-Policy Distillation (CCOPD) to improve multi-turn language model performance by mitigating 'self-anchored drift,' ensuring consistent answers regardless of whether the evidence is presented in a single prompt or gradually across multiple turns.

The paper introduces MemPoison, a novel memory poisoning attack that successfully injects triggerable backdoors into LLM agents' long-term memory through conversational interactions, achieving high attack success rates by bypassing selective memory mechanisms.

The paper introduces AnyMo, a unified multimodal framework that enables high-quality, scalable conditional human motion generation by leveraging a massive, cross-modal dataset and a masked modeling transformer.

The paper proposes MemPoison, a novel memory poisoning attack that injects triggerable backdoors into LLM agents' long-term memory through dialogue interactions, achieving high success rates by bypassing selective memory mechanisms.

The paper introduces DEBENCH, a novel framework that evaluates binary decompilers based on three orthogonal dimensions—readability, recompilability, and functionality—revealing that functional recovery is significantly harder than simple code readability.

This paper introduces Agents-K1, an end-to-end knowledge orchestration pipeline that converts raw documents into agent-native scientific knowledge graphs.