Prompt injection attacks can self-replicate across LLM agents in multi-agent systems, enabling data theft, misinformation, and system disruption while propagating silently.
On the resilience of llm-based multi-agent collaboration with faulty agents
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
HAM³ achieves up to 78.3% attack success rate on the GQA benchmark by hierarchically attacking perception, communication, and reasoning layers in multi-modal multi-agent systems.
Identifies concrete attacks from a malicious Provider on SAGA and proposes SAGA-BFT, SAGA-MON, SAGA-AUD, and SAGA-HYB mitigations offering different security-performance trade-offs.
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.
LATTE coordinates LLM agent teams with an evolving shared task graph, cutting token use, time, and failures while matching or beating accuracy of MetaGPT, leader-worker, and static methods.
StepFinder turns execution logs into temporal semantic sequences via LLMs then uses temporal modeling plus attention to attribute failures to specific steps more accurately and 79% faster than direct LLM methods on the Who&When benchmark.
Introduces six-dimension trustworthiness definition and attention-based A-Trust score with a TMS to improve LLM-MAS robustness against malicious or unreliable messages.
Context drift between agents causes hallucinations in multi-agent LLMs; the Shared State Verification Protocol reduces them more effectively than full-broadcast synchronization with 58% fewer API calls.
Generative multi-agent systems exhibit emergent collusion and conformity behaviors that cannot be prevented by existing agent-level safeguards.
LLM-agent simulations of hierarchical healthcare robot teams show team structure as the primary bottleneck for coordination success, more than model capability or added context, while revealing a trade-off between agent autonomy and system stability.
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
citing papers explorer
-
Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
Prompt injection attacks can self-replicate across LLM agents in multi-agent systems, enabling data theft, misinformation, and system disruption while propagating silently.
-
Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning
HAM³ achieves up to 78.3% attack success rate on the GQA benchmark by hierarchically attacking perception, communication, and reasoning layers in multi-modal multi-agent systems.
-
Attacks and Mitigations for Distributed Governance of Agentic AI under Byzantine Adversaries
Identifies concrete attacks from a malicious Provider on SAGA and proposes SAGA-BFT, SAGA-MON, SAGA-AUD, and SAGA-HYB mitigations offering different security-performance trade-offs.
-
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.
-
Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs
LATTE coordinates LLM agent teams with an evolving shared task graph, cutting token use, time, and failures while matching or beating accuracy of MetaGPT, leader-worker, and static methods.
-
StepFinder: A Temporal Semantic Framework for Failure Attribution in Multi-Agent Systems
StepFinder turns execution logs into temporal semantic sequences via LLMs then uses temporal modeling plus attention to attribute failures to specific steps more accurately and 79% faster than direct LLM methods on the Who&When benchmark.
-
To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems
Introduces six-dimension trustworthiness definition and attention-based A-Trust score with a TMS to improve LLM-MAS robustness against malicious or unreliable messages.
-
Hallucination as Context Drift: Synchronization Protocols for Multi-Agent LLM Systems
Context drift between agents causes hallucinations in multi-agent LLMs; the Shared State Verification Protocol reduces them more effectively than full-broadcast synchronization with 58% fewer API calls.
-
Emergent Social Intelligence Risks in Generative Multi-Agent Systems
Generative multi-agent systems exhibit emergent collusion and conformity behaviors that cannot be prevented by existing agent-level safeguards.
-
Before Humans Join the Team: Diagnosing Coordination Failures in Healthcare Robot Team Simulation
LLM-agent simulations of hierarchical healthcare robot teams show team structure as the primary bottleneck for coordination success, more than model capability or added context, while revealing a trade-off between agent autonomy and system stability.
-
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
- Opinion Polarization in LLM-Based Social Networks: Manipulation and Mitigation