AI agents can inspect code and run tests to support smart contract security. SlowMist reports about $38.6 billion in losses across the broader blockchain ecosystem. Existing evaluations can reward memorized or copied answers, including attack code recovered from public blockchain transactions. Reconstructing contracts...
Zi-Fan Peng, Peng Huang, Jing-Yi Zheng et al.· 0 citations
Profile-DP is introduced, a policy-aware local differential privacy framework designed specifically for user-profile release in personalized LLM inference, which provably bounds the release of user-withheld facts while treating public instructions, profile schemas, and authorized facts as public side information.
Mingchen Li, Zi-Fan Peng, Ke-Wei Sha et al.· 0 citations
This work introduces AlphaOpsBench, which evaluates end-to-end operationalization from source-grounded economic hypotheses to auditable executable programs over 581 source-preserving strategy records and a lifecycle-scale Polymarket dataset, and separates strategy fidelity, behavioral validity, historical executability...
Huai-Yu Jia, Ming-Xuan Zhao, Jin-Cheng Gao et al.· 1 citation
Internet memes are a pervasive form of multimodal online communication; however, such communication often involves users from diverse linguistic and cultural backgrounds. Therefore, adapting memes across cultures and languages is a central challenge for enabling mutual understanding in online communication. Unlike ordi...
Jingyi Zheng, Yu-Le Liu, Zi-Fan Peng et al.· 0 citations
TxSum is formulated, a new domain-grounded NLP task for DeFi transaction explanation, and MATEX, a grounded multi-agent framework for high-stakes transaction explanation is introduced, which achieves the strongest overall explanation quality.
Zifan Peng, Jingyi Zheng, Yule Liu et al.· 1 citation
Evaluations of LLM-based security assistants should jointly measure whether models respond, whether their usable responses are correct, and whether their outputs remain actionable across the engineering workflow.
Mingchen Li, M. Qiu, Zifan Peng et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.