arXiv AI
A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 25
On the Effectiveness of Kernel-Level Evidence for Agent Security
The paper introduces the Agent Cross‑Layer Evidence (ACE) corpus, pairing application‑level telemetry with kernel‑level syscall traces to study agent security. It shows that kernel evidence alone is discriminative and that combining it with application‑level data outperforms either layer alone, revealing complementary signals. The study also demonstrates that this cross‑layer approach generalizes to unseen attack families and works across different agent runtimes.
arXiv AI
Jun 16
The Proxy Knows Too Much: Sealing LLM API Routers with Attested TEEs
arXiv:2606. 16358v1 Announce Type: cross Abstract: Agents increasingly access large language models (LLMs) through API routers.
arXiv AI
Oct 15
ChannelGuard: From Borrowed Safety to Application-Controlled Defenses in Multi-Agent LLMs
ChannelGuard introduces an application‑controlled defense that inspects information at every handoff between models in multi‑agent LLM systems, eliminating the need for extra training or model calls. In over 5,700 test runs across five agent models, it stopped all attacks hidden in tool outputs, and on two open models it reduced successful prompt attacks from 80% to 3% and from 77% to 10%, without affecting accuracy on 30 math problems. The study shows that safety scores can mask very different underlying protections, and that relying solely on model or provider filters may be risky if either changes.
arXiv Machine Learning
Aug 24
RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry
RouteScan is a non‑intrusive auditing framework that detects harmful behavior in Mixture‑of‑Experts (MoE) large language models by analyzing expert‑routing telemetry captured from GPU execution. It uses the number of active GPU threads during the prefilling phase as a micro‑architectural fingerprint to isolate cross‑domain risk indicators and precisely identify malicious prompts. Evaluations on four open‑source MoE LLMs show strong generalization with AUROC > 0.91 on unseen harmful domains, while privacy tests indicate that full prompts cannot be reliably recovered from aggregated telemetry.
arXiv AI
Oct 15
ProtoArena: Can AI Agents Discover and Exploit Real-World Cross-Component Protocol Vulnerabilities?
ProtoArena is a new black-box benchmark that tests AI agents on 80 cross‑component vulnerability‑exploitation environments across 11 protocol and application domains and 7 attack categories. It evaluates agents at three information levels—guided reproduction, exploitation with context, and effect‑directed black‑box exploration—using a hybrid verifier that combines rule‑based checks with LLM review of traffic and logs. In experiments, Claude Opus 4.8 achieved the highest success rates, reaching 48.8% under guided conditions and 12.5% in effect‑directed black‑box scenarios, while also demonstrating significant DNSBomb optimization performance.
arXiv AI
Oct 12
Agentic Peer-to-Peer Networks: From Content Distribution to Capability and Action Sharing
The paper discusses how the shift from centralized AI APIs to local edge inference enables Client‑Side Autonomous Agents (CSAAs) that collaborate in Agentic Peer‑to‑Peer (P2P) networks. Unlike traditional P2P systems that exchange static content, these networks share dynamic, heterogeneous capabilities that may be unsafe, necessitating semantic discovery, drift management, and risk‑aware execution. The authors propose a plane‑based reference architecture, signed soft‑state capability descriptors for intent‑aware routing, and a tiered verification spectrum (reputation, canary probes, cryptographic evidence) to align trust costs with task risks, showing improved workflow success in simulations.