ILP-guided CEGIS evolves deployed expert safety rules for LLM agents from annotated traces, raising F1 to 0.98 (code) and 0.93 (embodied) in 4–5 iterations.
LLM Agents Should Employ Security Principles
11 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
11
Pith papers citing it
2
external citations · external index
citation-role summary
background 3
citation-polarity summary
years
2026 11roles
background 3representative citing papers
Multi-agent LLM frameworks can spread compromises across agent boundaries via insecure memory inheritance during subagent spawning.
Parallax enforces structural separation between AI thinking and acting via independent multi-tier validation, information flow control, and state rollback, blocking 98.9% of 280 adversarial attacks with zero false positives even when the reasoning system is fully compromised.
An independent reproduction on AgentDojo with Qwen2.5-7B finds that the Progent out-of-band defense reduces mean attack success from 25.8% to 4.2% and holds against a hand-crafted adaptive attack at 2.6%.
Introduces a compositional governance framework defining delegation types, resource scope attenuation, and an overlay operator for agentic AI authorization policies.
A survey providing a taxonomy of TEE platforms, an agent-centric threat model, and open challenges for applying confidential computing to secure agentic AI systems.
Protected policy placements in LLM agents maintain integrity under replay pressure on AutoGen and OpenHands traces, unlike task-local placements which show eviction or weakening.
Researchers developed a fast XGBoost-based detector using 42 runtime features to spot adversarial interaction patterns in LLM agents, running over 9 times faster than LLM detectors on synthetic multi-turn data.
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.
Frontier AI agents introduce new confidentiality, integrity, and availability risks through changed assumptions on code-data separation and authority boundaries, requiring layered defenses like sandboxing and policy enforcement.
citing papers explorer
-
AutoSpec: Safety Rule Evolution for LLM Agents via Inductive Logic Programming
ILP-guided CEGIS evolves deployed expert safety rules for LLM agents from annotated traces, raising F1 to 0.98 (code) and 0.93 (embodied) in 4–5 iterations.
-
When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks
Multi-agent LLM frameworks can spread compromises across agent boundaries via insecure memory inheritance during subagent spawning.
-
Parallax: Why AI Agents That Think Must Never Act
Parallax enforces structural separation between AI thinking and acting via independent multi-tier validation, information flow control, and state rollback, blocking 98.9% of 280 adversarial attacks with zero false positives even when the reasoning system is fully compromised.
-
Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents
An independent reproduction on AgentDojo with Qwen2.5-7B finds that the Progent out-of-band defense reduces mean attack success from 25.8% to 4.2% and holds against a hand-crafted adaptive attack at 2.6%.
-
Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI
Introduces a compositional governance framework defining delegation types, resource scope attenuation, and an overlay operator for agentic AI authorization policies.
-
When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI
A survey providing a taxonomy of TEE platforms, an agent-centric threat model, and open challenges for applying confidential computing to secure agentic AI systems.
-
Ghost in the Context: Policy-Carriage Integrity in LLM Agents
Protected policy placements in LLM agents maintain integrity under replay pressure on AutoGen and OpenHands traces, unlike task-local placements which show eviction or weakening.
-
A Low-Latency Fraud Detection Layer for Detecting Adversarial Interaction Patterns in LLM-Powered Agents
Researchers developed a fast XGBoost-based detector using 42 runtime features to spot adversarial interaction patterns in LLM agents, running over 9 times faster than LLM detectors on synthetic multi-turn data.
-
Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.
-
Security Considerations for Artificial Intelligence Agents
Frontier AI agents introduce new confidentiality, integrity, and availability risks through changed assumptions on code-data separation and authority boundaries, requiring layered defenses like sandboxing and policy enforcement.
- Safeguarding LLM Agents from Misalignment through Provenance Analysis