Copertina

Teams of LLM Agents can Exploit Zero-Day Vulnerabilities

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhu, Yuxuan, Kellermann, Antony, Gupta, Akul, Li, Philip, Fang, Richard, Bindu, Rohan, Kang, Daniel
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Multiagent Systems Artificial Intelligence I.2.7; D.4.6
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Predicting Known Vulnerabilities from Attack Descriptions Using Sentence Transformers
di: Othman, Refat
Pubblicazione: (2026)

CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities
di: Zhu, Yuxuan, et al.
Pubblicazione: (2025)

The Automation Advantage in AI Red Teaming
di: Mulla, Rob, et al.
Pubblicazione: (2025)

AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models
di: Dawson, Ads, et al.
Pubblicazione: (2025)

DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows
di: Gao, Yuxuan, et al.
Pubblicazione: (2026)

Benefits and Limitations of Communication in Multi-Agent Reasoning
di: Rizvi-Martel, Michael, et al.
Pubblicazione: (2025)

Hidden in Memory: Sleeper Memory Poisoning in LLM Agents
di: Pulipaka, Sidharth, et al.
Pubblicazione: (2026)

The Power of Stories: Narrative Priming Shapes How LLM Agents Collaborate and Compete
di: Großmann, Gerrit, et al.
Pubblicazione: (2025)

Refusal Evaluation in Coding LLMs and Code Agents: A Systematic Review of Thirteen Malicious-Code Prompt Corpora (2023-2025)
di: Young, Richard J., et al.
Pubblicazione: (2026)

AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification
di: Zhang, Tian, et al.
Pubblicazione: (2026)

Self-Emotion Blended Dialogue Generation in Social Simulation Agents
di: Zhang, Qiang, et al.
Pubblicazione: (2024)

PAVE: A Cognitive Architecture for Legitimate Violation in Generative Agent Societies
di: Yehia, Ahmad, et al.
Pubblicazione: (2026)

Exploring Design of Multi-Agent LLM Dialogues for Research Ideation
di: Ueda, Keisuke, et al.
Pubblicazione: (2025)

Multi-Agent Systems Powered by Large Language Models: Applications in Swarm Intelligence
di: Jimenez-Romero, Cristian, et al.
Pubblicazione: (2025)

PestMA: LLM-based Multi-Agent System for Informed Pest Management
di: Shi, Hongrui, et al.
Pubblicazione: (2025)

Quantifying Return on Security Controls in LLM Systems
di: Moulton, Richard Helder, et al.
Pubblicazione: (2025)

Review of Case-Based Reasoning for LLM Agents: Theoretical Foundations, Architectural Components, and Cognitive Integration
di: Hatalis, Kostas, et al.
Pubblicazione: (2025)

Literature Review Of Multi-Agent Debate For Problem-Solving
di: Tillmann, Arne
Pubblicazione: (2025)

MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents
di: Gowda, Ishrith
Pubblicazione: (2026)

Building Browser Agents: Architecture, Security, and Practical Solutions
di: Vardanyan, Aram
Pubblicazione: (2025)

Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation
di: Yao, Yiheng, et al.
Pubblicazione: (2026)

ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systems
di: Zhu, Andrew, et al.
Pubblicazione: (2024)

Governance Architecture for Autonomous Agent Systems: Threats, Framework, and Engineering Practice
di: Ge, Yuxu
Pubblicazione: (2026)

Solving Zebra Puzzles Using Constraint-Guided Multi-Agent Systems
di: Berman, Shmuel, et al.
Pubblicazione: (2024)

Detecting Prompt Injection Attacks Against Application Using Classifiers
di: Shaheer, Safwan, et al.
Pubblicazione: (2025)

Beyond the Benchmark: Innovative Defenses Against Prompt Injection Attacks
di: Shaheer, Safwan, et al.
Pubblicazione: (2025)

CRAwDAD: Causal Reasoning Augmentation with Dual-Agent Debate
di: Vamosi, Finn G., et al.
Pubblicazione: (2025)

Agent WARPP: Workflow Adherence via Runtime Parallel Personalization
di: Mazzolenis, Maria Emilia, et al.
Pubblicazione: (2025)

LLM Agents can Autonomously Exploit One-day Vulnerabilities
di: Fang, Richard, et al.
Pubblicazione: (2024)

SweEval: Do LLMs Really Swear? A Safety Benchmark for Testing Limits for Enterprise Use
di: Patel, Hitesh Laxmichand, et al.
Pubblicazione: (2025)

GSAR: Typed Grounding for Hallucination Detection and Recovery in Multi-Agent LLMs
di: Kamelhar, Federico A.
Pubblicazione: (2026)

A Knowledge-Based Language Model: Deducing Grammatical Knowledge in a Multi-Agent Language Acquisition Simulation
di: Shakouri, David Ph., et al.
Pubblicazione: (2025)

Continuous Discovery of Vulnerabilities in LLM Serving Systems with Fuzzing
di: Zhao, Yunze, et al.
Pubblicazione: (2026)

TRIZ Agents: A Multi-Agent LLM Approach for TRIZ-Based Innovation
di: Szczepanik, Kamil, et al.
Pubblicazione: (2025)

RPRA: Predicting an LLM-Judge for Efficient but Performant Inference
di: Ashley, Dylan R., et al.
Pubblicazione: (2026)

DURA-CPS: A Multi-Role Orchestrator for Dependability Assurance in LLM-Enabled Cyber-Physical Systems
di: Srinivasan, Trisanth, et al.
Pubblicazione: (2025)

ORACLE-SWE: Quantifying the Contribution of Oracle Information Signals on SWE Agents
di: Li, Kenan, et al.
Pubblicazione: (2026)

SBASH: a Framework for Designing and Evaluating RAG vs. Prompt-Tuned LLM Honeypots
di: Adebimpe, Adetayo, et al.
Pubblicazione: (2025)

AegisShield: Democratizing Cyber Threat Modeling with Generative AI
di: Grofsky, Matthew
Pubblicazione: (2025)

Evaluating the Reliability of Digital Forensic Evidence Discovered by Large Language Model: A Case Study
di: Khatiwala, Jeel Piyushkumar, et al.
Pubblicazione: (2026)