Newest papers

Connection Escrow: Holding AI-Agent Pod Egress in the Kernel Until an Isolated Verifier Rules

Ashok Subbabhatta Gopalakrishna · 2026 · arXiv

DOI: 10.48550/arXiv.2610.26501 · open-access PDF

Arabic

يعمل العمال الذكاء الاصطناعي في المكونات من خلال فتح اتصالات الشبكة ، ويمكن أن يكون النص الذي يحركها عدوانية. يتم تجنب التحكمات التي يتم وضعها بين المكون والمعدات من خلال عملية طفل أو اتصال مباشر ، ولا يتم اتخاذ موافقة منهم على الاتصال الذي يفتح القسم في وقت لاحق. نحن نقدم اتصال متصل: يتم تجنب كل اتصال TCP الناجح من قاعدة مراقبة داخل طريق connect() القسم ، قبل وجود أي حزمة ، من قبل برنامج eBPF 98 الإرشادات في cgroup القسم.

Machine translation (Meta M2M100); the English original follows.

Abstract

AI agents in containers act by opening network connections, and the text that drives them can be hostile. Controls placed between the agent and its tools are bypassed by a child process or a direct socket, and their approval is not tied to the connection the kernel later opens. We present connection escrow: every outbound TCP connection from a supervised pod is parked inside the kernel's connect() path, before any packet exists, by a 98-instruction eBPF program on the pod's cgroup. A node interceptor attributes the held socket to its kernel socket cookie, process, executable digest, cgroup and

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26501, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange