collaborators

6 papers

cs.CR2026

Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection

Xulin Hu, Che Wang, Wei Yang Bryan Lim +2

Representation Engineering analyses often characterize refusal using static directions extracted from terminal or pooled representations. We ask whether this view misses how refusa…

cs.DC2026

A402: Binding Cryptocurrency Payments to Service Execution for Agentic Commerce

Yue Li, Lei Wang, Kaixuan Wang +4

The rapid proliferation of autonomous AI agents is driving a shift toward agentic commerce, where agents are expected to autonomously invoke and pay for services. While blockchain-…

cs.CR2026

AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs

Che Wang, Jiaming Zhang, Ziqi Zhang +6

The integration of external data services (e.g., Model Context Protocol, MCP) has made large language model-based agents increasingly powerful for complex task execution. However,…

cs.AI2026

ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction

Che Wang, Fuyao Zhang, Jiaming Zhang +6

Large Language Model (LLM) agents are susceptible to Indirect Prompt Injection (IPI) attacks, where malicious instructions in retrieved content hijack the agent's execution. Existi…

cs.SE2024

ContractTinker: LLM-Empowered Vulnerability Repair for Real-World Smart Contracts

Che Wang, Jiashuo Zhang, Jianbo Gao +3

Smart contracts are susceptible to being exploited by attackers, especially when facing real-world vulnerabilities. To mitigate this risk, developers often rely on third-party audi…

cs.CR2024

Demystifying and Detecting Cryptographic Defects in Ethereum Smart Contracts

Jiashuo Zhang, Yiming Shen, Jiachi Chen +5

Ethereum has officially provided a set of system-level cryptographic APIs to enhance smart contracts with cryptographic capabilities. These APIs have been utilized in over 10% of E…