NRT-Bench reports that adaptive multi-turn attacks cause critical safety function loss in 8.7-12.1% of sessions across four frontier LLM operator models, with nearly disjoint vulnerabilities and strongly model-dependent defense effects.
BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
abstract
The security of LLM-based multi-agent systems (MAS) is critically threatened by propagation vulnerability, where malicious agents can distort collective decision-making through inter-agent message interactions. While existing supervised defense methods demonstrate promising performance, they may be impractical in real-world scenarios due to their heavy reliance on labeled malicious agents to train a supervised malicious detection model. To enable practical and generalizable MAS defenses, in this paper, we propose BlindGuard, an unsupervised defense method that learns without requiring any attack-specific labels or prior knowledge of malicious behaviors. To this end, we establish a hierarchical agent encoder to capture individual, neighborhood, and global interaction patterns of each agent, providing a comprehensive understanding for malicious agent detection. Meanwhile, we design a corruption-guided detector that consists of directional noise injection and contrastive learning, allowing effective detection model training solely on normal agent behaviors. Extensive experiments show that BlindGuard effectively detects diverse attack types (i.e., prompt injection, memory poisoning, and tool attack) across MAS with various communication patterns while maintaining superior generalizability compared to supervised baselines. The code is available at: https://github.com/MR9812/BlindGuard.
citation-role summary
background 2
citation-polarity summary
years
2026 9roles
background 2polarities
background 2representative citing papers
CASPIAN introduces unified cross-channel causal monitoring via late-interaction conditional transfer entropy to detect cascade onset and attribute origin, bridge, and amplifier agents in LLM multi-agent systems.
FlowSteer is a prompt-only attack that biases multi-agent LLM workflow planning to propagate malicious signals, raising success rates by up to 55%, with FlowGuard as an input-side defense reducing it by up to 34%.
PropGuard is a propagation-aware framework for LLM-MAS that constructs dual-view spatio-temporal graphs, employs a GE-GRPO inspector to recover suspicious subgraphs, and applies source-guided remediation to lower attack success while preserving task performance.
Embedding-based defenses fail against crafted attacks in LLM MAS; confidence scores from logits improve robustness but decay over communication rounds.
Activation-space divergence detects and corrects compromised LLM agents in multi-agent systems without interaction graphs or synchronized rounds, outperforming graph baselines especially under async stealthy attacks.
MESA ranks MAS communication edges by vulnerability via graph-theoretic metrics and dynamic probes, achieving mean Spearman ρ=+0.60 correlation with empirical per-edge attack success and 3x interception gain when monitoring the top 10%.
SAIGuard uses communication-state simulation on the MAS interaction graph to detect and sanitize risky messages via reconstruction deviations, reducing attack success while preserving utility.
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.
citing papers explorer
-
NRT-Bench: Benchmarking Multi-Turn Red-Teaming of LLM Operator Agents in Safety-Critical Control Rooms
NRT-Bench reports that adaptive multi-turn attacks cause critical safety function loss in 8.7-12.1% of sessions across four frontier LLM operator models, with nearly disjoint vulnerabilities and strongly model-dependent defense effects.
-
CASPIAN: Online Detection and Attribution of Cascade Attacks in LLM Multi-Agent Systems via Cross-Channel Causal Monitoring
CASPIAN introduces unified cross-channel causal monitoring via late-interaction conditional transfer entropy to detect cascade onset and attribute origin, bridge, and amplifier agents in LLM multi-agent systems.
-
FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
FlowSteer is a prompt-only attack that biases multi-agent LLM workflow planning to propagate malicious signals, raising success rates by up to 55%, with FlowGuard as an input-side defense reducing it by up to 34%.
-
PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and Remediation
PropGuard is a propagation-aware framework for LLM-MAS that constructs dual-view spatio-temporal graphs, employs a GE-GRPO inspector to recover suspicious subgraphs, and applies source-guided remediation to lower attack success while preserving task performance.
-
When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems
Embedding-based defenses fail against crafted attacks in LLM MAS; confidence scores from logits improve robustness but decay over communication rounds.
-
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems
Activation-space divergence detects and corrects compromised LLM agents in multi-agent systems without interaction graphs or synchronized rounds, outperforming graph baselines especially under async stealthy attacks.
-
MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems
MESA ranks MAS communication edges by vulnerability via graph-theoretic metrics and dynamic probes, achieving mean Spearman ρ=+0.60 correlation with empirical per-edge attack success and 3x interception gain when monitoring the top 10%.
-
SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent Systems
SAIGuard uses communication-state simulation on the MAS interaction graph to detect and sanitize risky messages via reconstruction deviations, reducing attack success while preserving utility.
-
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.