Imagen de Portada

SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Najt, Elle, Toft, Colin, Tracy, Tyler, Roger, Fabien, Benton, Joe
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring
por: Jotautaitė, Monika, et al.
Publicado: (2026)

DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
por: Kang, Mintong, et al.
Publicado: (2023)

MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents
por: Zhang, Dongsen, et al.
Publicado: (2025)

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning
por: Domico, Kyle, et al.
Publicado: (2025)

SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents
por: Kutasov, Jonathan, et al.
Publicado: (2025)

Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
por: Zhang, Hanrong, et al.
Publicado: (2024)

WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
por: Evtimov, Ivan, et al.
Publicado: (2025)

CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios
por: Lim, Taein, et al.
Publicado: (2026)

AttackSeqBench: Benchmarking the Capabilities of LLMs for Attack Sequences Understanding
por: Ma, Haokai, et al.
Publicado: (2025)

EaTVul: ChatGPT-based Evasion Attack Against Software Vulnerability Detection
por: Liu, Shigang, et al.
Publicado: (2024)

Reliable Model Watermarking: Defending Against Theft without Compromising on Evasion
por: Zhu, Hongyu, et al.
Publicado: (2024)

BashArena: A Control Setting for Highly Privileged AI Agents
por: Kaufman, Adam, et al.
Publicado: (2025)

Securing AI Agents Against Prompt Injection Attacks
por: Ramakrishnan, Badrinath, et al.
Publicado: (2025)

Attack Selection Reduces Safety in Concentrated AI Control Settings against Trusted Monitoring
por: Schaeffer, Joachim, et al.
Publicado: (2026)

MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks
por: Zhang, Xinkai, et al.
Publicado: (2026)

AttackPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents
por: Wu, Yixin, et al.
Publicado: (2025)

VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents
por: Cao, Tri, et al.
Publicado: (2025)

ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models
por: Liu, Xuxu, et al.
Publicado: (2025)

ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents
por: Lee, Seunghyun, et al.
Publicado: (2026)

AutoPenBench: Benchmarking Generative Agents for Penetration Testing
por: Gioacchini, Luca, et al.
Publicado: (2024)

Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussions
por: Xiang, Qiuchi, et al.
Publicado: (2026)

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt
por: Wang, Zhilong, et al.
Publicado: (2025)

Narrow Secret Loyalty Dodges Black-Box Audits
por: Lamerton, Alfie, et al.
Publicado: (2026)

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
por: Zhu, Kaijie, et al.
Publicado: (2025)

Decoding Deception: Understanding Automatic Speech Recognition Vulnerabilities in Evasion and Poisoning Attacks
por: G, Aravindhan, et al.
Publicado: (2025)

SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
por: Yin, Sheng, et al.
Publicado: (2024)

Enhancing O-RAN Security: Evasion Attacks and Robust Defenses for Graph Reinforcement Learning-based Connection Management
por: Balakrishnan, Ravikumar, et al.
Publicado: (2024)

LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection
por: Zhao, Lei, et al.
Publicado: (2026)

Temporal UI State Inconsistency in Desktop GUI Agents: Formalizing and Defending Against TOCTOU Attacks on Computer-Use Agents
por: Xu, Wenpeng
Publicado: (2026)

CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks
por: Li, Siyuan, et al.
Publicado: (2026)

MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks
por: Syros, Georgios, et al.
Publicado: (2026)

Monitoring Decomposition Attacks in LLMs with Lightweight Sequential Monitors
por: Yueh-Han, Chen, et al.
Publicado: (2025)

Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack
por: Wang, Hao, et al.
Publicado: (2026)

SecRepoBench: Benchmarking Code Agents for Secure Code Completion in Real-World Repositories
por: Shen, Chihao, et al.
Publicado: (2025)

Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks
por: Xiang, Chong, et al.
Publicado: (2026)

When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents
por: Liu, Shi, et al.
Publicado: (2026)

LLM Watermark Evasion via Bias Inversion
por: Hwang, Jeongyeon, et al.
Publicado: (2025)

A Model Stealing Attack Against Multi-Exit Networks
por: Pan, Li, et al.
Publicado: (2023)

Analysis of LLMs Against Prompt Injection and Jailbreak Attacks
por: Jaiswal, Piyush, et al.
Publicado: (2026)

Defenses Against Prompt Attacks Learn Surface Heuristics
por: Li, Shawn, et al.
Publicado: (2026)