会员服务
FinBalance: A Multi-Document Accounting Reconciliation Benchmark
Arxiv
0+阅读 · 6月14日
Trust Without Trusting: A Recomputable Trust Protocol for Autonomous Agents
Arxiv
0+阅读 · 6月14日
Value Functions as Supermartingale Certificates
Arxiv
0+阅读 · 5月29日
GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines
Arxiv
0+阅读 · 6月7日
PriSrv: Privacy-Enhanced and Highly Usable Service Discovery in Wireless Communications
Arxiv
0+阅读 · 6月4日
Upholding Epistemic Agency: A Brouwerian Assertibility Constraint for Responsible AI
Arxiv
0+阅读 · 5月9日
Heartbeat-Bound Hierarchical Credentials: Cryptographic Revocation for AI Agent Swarms
Arxiv
0+阅读 · 5月20日
Biprofile Deviation Logic: Report-Replacement Frames and Audit Witnesses
Arxiv
0+阅读 · 5月4日
Caught in the Act(ivation): Toward Pre-Output and Multi-Turn Detection of Credential Exfiltration by LLM Agents
Arxiv
0+阅读 · 6月2日
Credential Disclosure in (EU) Digital Identity Wallets: Privacy Risks and Practical Mitigations
Arxiv
0+阅读 · 6月4日
Triple-Identity Authentication: The Future of Secure Access
Arxiv
0+阅读 · 5月5日
When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI
Arxiv
0+阅读 · 5月7日
Duality for Optimal Multi-Item, Multi-Bidder Auction Design: Revenue Certificates through Deep Learning
Arxiv
0+阅读 · 6月8日
Will the Agent Recuse Itself? Measuring LLM-Agent Compliance with In-Band Access-Deny Signals
Arxiv
0+阅读 · 6月4日
Zero-Error Recovery under Deterministic Partial Views: Matroid Bounds and Verifiable Realizability
Arxiv
0+阅读 · 4月30日
参考链接
微信扫码咨询专知VIP会员
Top