InfoResearchPeer-reviewedLLM-specific
Securing next-generation edge intelligence: A survey from federated learning to autonomous agents in cyber-physical systems
- Published
- Record updated
Summary
This survey reviews threats to autonomous edge agents built on LLMs and SLMs in cyber-physical systems and IoT, organizing them across Perception, Cognition, Actuation and Collaboration layers. It finds that several attacks have been demonstrated on physical platforms, including jailbreaking a deployed commercial robot, while multi-agent attacks run only in simulation and software. It identifies three edge-induced threats that no surveyed edge-deployable runtime mechanism addresses: energy-targeted resource exhaustion, quantization-specific evasion, and model provenance against supply-chain weight poisoning.
Topics
Related items
- InfoIn Other News: New CISA Director Nominee, Connected Car Hacking, Baker Tilly Data BreachSimilar attack · SecurityWeek
- MediumHow one AI agent exposed five critical enterprise security gapsSimilar attack · BleepingComputer
- InfoCapLite: Prompt-Injection Defense for Small Language Model Agents without Model-Written Security ArtifactsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
- MediumTrained to betray: How post-training supply chain attacks hijack coding agentsSimilar attack · Microsoft Security Blog
- InfoMobileProbe: Adaptive Security Evaluation of Mobile Agents via Trajectory-Aware InjectionSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)