The Proxy Knows Too Much: Sealing LLM API Routers with Attested TEEs

• URL: http://arxiv.org/abs/2606.16358v1
• Date: Mon, 15 Jun 2026 07:55:13 GMT
• Title: The Proxy Knows Too Much: Sealing LLM API Routers with Attested TEEs
• Abstract summary: AEGIS is a provider-transparent API router whose data path is a client-verified faithful passthrough.<n>We show that all four malicious-router attack classes succeed against a plaintext-access baseline.<n>The trusted path is $851$ lines, carries three provider-native APIs without conversion, and completes every request under real-provider workload and typos.
• Score: 14.19502587458358
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agents increasingly access large language models (LLMs) through API routers. A router terminates the client's transport-layer security session and opens a separate upstream session, so it holds the full interaction in plaintext. This makes the router an application-layer man-in-the-middle: it can rewrite agent tool calls, swap dependencies for typosquatted packages, trigger attacks only under audit-evading conditions, and passively exfiltrate secrets. Existing client-side defenses are evadable. We propose AEGIS, a provider-transparent attested API router whose data path is a client-verified faithful passthrough. AEGISconfines plaintext handling to a small hardware-enclave component while leaving authentication, scheduling, accounting, and management on the untrusted host. The client verifies the enclave before releasing plaintext. The host can neither read nor alter the interaction, and plaintext leaves only toward destinations fixed by the measured image. We show that all four malicious-router attack classes succeed against a plaintext-access baseline and are blocked by AEGIS, including adaptive tests against the same boundary. The trusted path is $851$ lines, carries three provider-native APIs without conversion, and completes every request under real-provider workload and concurrency. In a seeded audit pilot, two commodity coding agents find eight and ten of ten planted invariant violations. The local relay overhead is about six milliseconds per request.

Related papers

• Privacy-Preserving Topology-Guided Safety for LLM-Based Multi-Agent Systems via Federated Graph Learning [67.04448659688579]
  FGLGuard cuts AgentDojo's ground-success rate by 43% at near-unguarded utility, zero API cost, and negligible capability loss.<n>Federation is not optional: off-the-shelf transfer collapses under distribution shift.<n>Live FGLGuard cuts AgentDojo's ground-success rate by 43% at near-unguarded utility, zero API cost, and negligible capability loss.
  arXiv  Detail & Related papers  (2026-09-02T07:57:12Z)
• ROPE: Routed Origin Policy Enforcement against Indirect Prompt Injection [61.4148196085256]
  We present ROPE (Routed Origin Policy Enforcement), which is anchored in a structural notion of trust.<n>Our approach admits two provable guarantees: 1) at every step of a trajectory, no value whose only origin is attacker-writable content reaches an origin-guarded parameter, and 2) no rewording of an injection changes an admission decision.
  arXiv  Detail & Related papers  (2026-08-27T01:22:14Z)
• LMSM: LLM Security Framework Inspired by Linux Security Modules [56.93644694627783]
  Large language models (LLMs) are increasingly deployed with layered defenses, yet malicious prompts can still bypass them.<n>We present Language Model Security Modules (LMSM), a security framework that adapts the separation behind Linux Security Modules (LSM) to LLM serving.
  arXiv  Detail & Related papers  (2026-08-26T12:13:05Z)
• KeyPooling: Measuring Where LLM API Relay Paths Collapse Prompt Cache Isolation [53.952294884822955]
  Large language model (LLM) API relays authenticate customers separately but often forward requests through shared provider credentials.<n>We present KeyPooling, a measurement method that traces customer identity through cache lookup and write.<n>We derive a defense contract: every customer must enter a provider-enforced domain.
  arXiv  Detail & Related papers  (2026-08-18T08:12:34Z)
• Good Agentic Friends Do Not Just Give Verbal Advice: They Can Update Your Weights [58.27172968382275]
  Multi-agent LLM systems usually collaborate by exchanging natural-language messages.<n>We study an alternative communication interface: instead of appending a sender's message to the receiver's context, compile the sender's hidden states into a transient, receiver-specific weight perturbation.
  arXiv  Detail & Related papers  (2026-05-13T17:58:32Z)
• CapSeal: Capability-Sealed Secret Mediation for Secure Agent Execution [1.9473631530390483]
  CapSeal is a capability-sealed secret mediation architecture that replaces direct secret access with constrained invocations through a local trusted broker.<n>We describe a Rust prototype integrated with an MCP-facing adapter, formulate conditional security goals for non-disclosure, constrained use, replay resistance, and auditability.
  arXiv  Detail & Related papers  (2026-04-18T00:23:32Z)
• Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain [6.142057368768942]
  Large language model (LLM) agents increasingly rely on third-party API routers to dispatch tool-calling requests.<n>We present the first systematic study of this attack surface.
  arXiv  Detail & Related papers  (2026-04-09T16:06:41Z)
• AEGIS: No Tool Call Left Unchecked -- A Pre-Execution Firewall and Audit Layer for AI Agents [4.963079926145645]
  AEGIS is a pre-execution firewall and audit layer for AI agents.<n>It interposes on the tool-execution path and applies a three-stage pipeline.<n>High-risk calls can be held for human approval, and all decisions are recorded in a tamper-evident audit trail.
  arXiv  Detail & Related papers  (2026-03-13T03:49:12Z)
• Agentic Peer-to-Peer Networks: From Content Distribution to Capability and Action Sharing [10.47562113256175]
  This article outlines the networking foundations needed to make such collaboration practical.<n>We propose a plane-based reference architecture that decouples connectivity/identity, semantic discovery, and execution.<n>We also present a textittiered verification spectrum: Tier1 relies on reputation signals, Tier2 applies lightweight canary challenge-response with fallback selection, and Tier3 requires evidence packages such as signed tool receipts/traces.
  arXiv  Detail & Related papers  (2026-03-04T05:58:44Z)
• BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents [58.83028403414688]
  Large language model (LLM) agents execute tasks through multi-step workflow that combine planning, memory, and tool use.<n>Backdoor triggers injected into specific stages of an agent workflow can persist through multiple intermediate states and adversely influence downstream outputs.<n>We propose textbfBackdoorAgent, a modular and stage-aware framework that provides a unified agent-centric view of backdoor threats in LLM agents.
  arXiv  Detail & Related papers  (2026-01-08T03:49:39Z)
• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• Agentic JWT: A Secure Delegation Protocol for Autonomous AI Agents [0.6747475365990533]
  In agentic settings reasoning, prompt injection, or multi-agent orchestration can silently expand privileges.<n>We introduce Agentic JWT (A-JWT), a dual-faceted intent token that binds each agent's action to verifiable user intent.<n>A-JWT carries an agent's identity as a one-way hash derived from its prompt, tools and configuration.
  arXiv  Detail & Related papers  (2025-09-16T23:43:24Z)
• DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents [52.92354372596197]
  Large Language Models (LLMs) are increasingly central to agentic systems due to their strong reasoning and planning capabilities.<n>This interaction also introduces the risk of prompt injection attacks, where malicious inputs from external sources can mislead the agent's behavior.<n>We propose a Dynamic Rule-based Isolation Framework for Trustworthy agentic systems, which enforces both control and data-level constraints.
  arXiv  Detail & Related papers  (2025-06-13T05:01:09Z)
• EmInspector: Combating Backdoor Attacks in Federated Self-Supervised Learning Through Embedding Inspection [53.25863925815954]
  Federated self-supervised learning (FSSL) has emerged as a promising paradigm that enables the exploitation of clients' vast amounts of unlabeled data. While FSSL offers advantages, its susceptibility to backdoor attacks has not been investigated. We propose the Embedding Inspector (EmInspector) that detects malicious clients by inspecting the embedding space of local models.
  arXiv  Detail & Related papers  (2024-05-21T06:14:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.