Securing next-generation edge intelligence: A survey from federated learning to autonomous agents in cyber-physical systems

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

• AI agents

Related items

• InfoTop agent skill security resources — November 2026Similar attack · Adversa AI Blog
• InfoHow to Turn AI Red Team Findings Into Runtime ControlsSimilar attack · Straiker Blog
• MediumDocker Sandboxes vulnerability lets AI agents access sensitive files outside their sandbox (CVE-2026-103916) | Endor LabsSimilar attack · Endor Labs Blog
• MediumFree the Model, Sell the Gateway: Prompt Adware hidden in Jailbreak BundlesSimilar attack · Check Point Research
• InfoRight Tool, Wrong Parameters: Defending LLM Agents Against Parameter PoisoningSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)