AgentVisor cuts prompt injection success rate to 0.65% in LLM agents with only 1.45% utility loss via semantic privilege separation and one-shot self-correction.
Defending against prompt injection with a few defensive tokens
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CR 4years
2026 4verdicts
UNVERDICTED 4representative citing papers
ASPO combines multi-agent LLM proposals with deterministic enforcement in a MAPE-K loop to select conflict-free, resource-feasible security patterns for IoT, delivering 100% safety invariants and 21-23% tail latency/energy reductions on testbed workloads.
Large-scale empirical study finds widespread prompt leaking in commercial LLM apps and introduces AREA defense that improves usability while resisting leaks.
The paper argues that agent security is best addressed as a systems problem by applying principles from operating systems, networks, and formal methods rather than relying solely on model robustness improvements.
citing papers explorer
-
AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization
AgentVisor cuts prompt injection success rate to 0.65% in LLM agents with only 1.45% utility loss via semantic privilege separation and one-shot self-correction.
-
Self-Adaptive Multi-Agent LLM-Based Security Pattern Selection for IoT Systems
ASPO combines multi-agent LLM proposals with deterministic enforcement in a MAPE-K loop to select conflict-free, resource-feasible security patterns for IoT, delivering 100% safety invariants and 21-23% tail latency/energy reductions on testbed workloads.
-
Understanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based Applications
Large-scale empirical study finds widespread prompt leaking in commercial LLM apps and introduces AREA defense that improves usability while resisting leaks.
-
Agent Security is a Systems Problem
The paper argues that agent security is best addressed as a systems problem by applying principles from operating systems, networks, and formal methods rather than relying solely on model robustness improvements.