Author

Blaise Delattre

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

CAGE: Certified Authorization under Typed-Return Uncertainty for Tool-Using Agents

CAGE removes the in-budget false allows that accurate pointwise gates admit, while keeping a useful fraction of decisions autonomous across synthetic, policy-as-code, regulatory, and real-transaction settings.

Blaise Delattre, Cong Wang, Yang Cao · arXiv.org · 1 citation

Preprint Aug 2026

SynChain: Inducing Computer-Use Agent Systems to Construct Their Own Attack Chains

This work introduces SynChain, a self-synthesized attack paradigm utilizing persistence-aware directed supervised fine-tuning to induce agents to create poisoned yet benign-looking artifacts, proving that securing CUAs requires provenance-aware reasoning over cross-task execution trajectories.

Fu-Yao Zhang, Jia-Ming Zhang, Che Wang et al. · 0 citations