InfoResearchPreprintLLM-specific
Enforcing Accountable Disclosure in Confidential AI
- Published
- Record updated
Summary
CORDE is a system for confidential virtual machines that confines user-derived data by default and allows it to leave only after it is declared. A declaration records the exact contents, recipient and stated reason in a tamper-evident log that users can access. The authors combine per-user information-flow control in Rust with a TEE-based ledger and remote attestation. On an NVIDIA H100 GPU, declaring before disclosure adds about 0.5% task latency on the AppWorld agent benchmark.
Related items
- InfoHugging Face’s CEO Says His P(Doom) Is ‘Close to Zero’Same vendor · Wired (Security)
- InfoBuilding on open source AI? Hugging Face’s policy chief on the costs, risks, and trade-offsSame vendor · TechCrunch (Security)
- InfoCrowdStrike’s AI SOC vision evolves as agentic uncertainty adds new twistSame vendor · CSO Online
- InfoUS tech stocks recover after selloff spooks investors over AI spendingSame vendor · The Guardian Technology
- InfoChart: Anthropic's cash pile towers over nearly every U.S. companySame vendor · CNBC Technology