17 citations · 17 across the 2 of their papers we have counts for
2 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.SE2024★ 17 cited
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…