Edge-local LLM agent deployments on IoT eliminate routine cloud data exposure but degrade sovereignty during fallbacks and create exploitable failover windows, making architecture a primary security determinant.
From assistant to double agent: Formalizing and benchmarking attacks on OpenClaw for personalized local AI agent
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 9roles
background 2representative citing papers
A3S-Bench evaluates LLM agents against temporal, spatial, and semantic evasions, raising average risk trigger rates from 28.3% to 52.6% across 2,254 trajectories and 20 scenarios.
LivePI benchmark shows indirect prompt injection attack success rates of 10.7% to 29.6% across five AI models in live test environments covering seven input surfaces and multiple malicious goals.
Routine user chats can unintentionally poison the long-term state of personalized LLM agents, causing authorization drift, tool escalation, and unchecked autonomy, as measured by a new benchmark and reduced by the StateGuard defense.
Claw AI agents' heartbeat background execution shares memory context with user sessions, allowing ordinary social misinformation to silently pollute long-term memory and shape behavior at rates up to 76% across sessions.
HearthNet is an edge multi-agent orchestration system that runs role-specialized LLM agents locally to handle natural-language smart-home control, conflict resolution, and failure recovery through MQTT and shared state.
A runtime governance framework for embodied agents intercepts 96.2% of unauthorized actions and achieves 91.4% recovery success in 1000 simulation trials while outperforming baselines.
The paper develops a unified framework that organizes computer-use agent reliability around perception-decision-execution layers and creation-deployment-operation-maintenance stages to map security and alignment interventions.
The survey organizes security threats and defenses in autonomous LLM agents into four layers and identifies that risks can propagate across layers from inputs to ecosystem impacts.
citing papers explorer
-
Systems-Level Attack Surface of Edge Agent Deployments on IoT
Edge-local LLM agent deployments on IoT eliminate routine cloud data exposure but degrade sovereignty during fallbacks and create exploitable failover windows, making architecture a primary security determinant.
-
Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions
A3S-Bench evaluates LLM agents against temporal, spatial, and semantic evasions, raising average risk trigger rates from 28.3% to 52.6% across 2,254 trajectories and 20 scenarios.
-
LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injectio
LivePI benchmark shows indirect prompt injection attack success rates of 10.7% to 29.6% across five AI models in live test environments covering seven input surfaces and multiple malicious goals.
-
When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents
Routine user chats can unintentionally poison the long-term state of personalized LLM agents, causing authorization drift, tool escalation, and unchecked autonomy, as measured by a new benchmark and reduced by the StateGuard defense.
-
Mind Your HEARTBEAT! Claw Background Execution Inherently Enables Silent Memory Pollution
Claw AI agents' heartbeat background execution shares memory context with user sessions, allowing ordinary social misinformation to silently pollute long-term memory and shape behavior at rates up to 76% across sessions.
-
HearthNet: Edge Multi-Agent Orchestration for Smart Homes
HearthNet is an edge multi-agent orchestration system that runs role-specialized LLM agents locally to handle natural-language smart-home control, conflict resolution, and failure recovery through MQTT and shared state.
-
Harnessing Embodied Agents: Runtime Governance for Policy-Constrained Execution
A runtime governance framework for embodied agents intercepts 96.2% of unauthorized actions and achieves 91.4% recovery success in 1000 simulation trials while outperforming baselines.
-
Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability
The paper develops a unified framework that organizes computer-use agent reliability around perception-decision-execution layers and creation-deployment-operation-maintenance stages to map security and alignment interventions.
-
Security Attack and Defense Strategies for Autonomous Agent Frameworks: A Layered Review with OpenClaw as a Case Study
The survey organizes security threats and defenses in autonomous LLM agents into four layers and identifies that risks can propagate across layers from inputs to ecosystem impacts.