:: Library Catalog

Imagen de Portada

Guardado en:

Detalles Bibliográficos
Autores principales:	Jiang, Xiaochong, Yang, Shiqi, Li, Ziwei, Liu, Lifei, Yu, Haoran, Liu, Yichen
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Artificial Intelligence
Acceso en línea:	https://arxiv.org/abs/2605.26542
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SOK: A Taxonomy of Attack Vectors and Defense Strategies for Agentic Supply Chain Runtime
por: Jiang, Xiaochong, et al.
Publicado: (2026)

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems
por: Wang, Su, et al.
Publicado: (2026)

CapSeal: Capability-Sealed Secret Mediation for Secure Agent Execution
por: Jin, Shutong, et al.
Publicado: (2026)

SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents
por: Liang, Siyuan, et al.
Publicado: (2025)

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

The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck
por: Fan, Linfeng, et al.
Publicado: (2026)

Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents
por: Zhou, Kaiyu, et al.
Publicado: (2026)

SafeHarness: Lifecycle-Integrated Security Architecture for LLM-based Agent Deployment
por: Lin, Xixun, et al.
Publicado: (2026)

Evaluating Privilege Usage of Agents with Real-World Tools
por: Zhang, Quan, et al.
Publicado: (2026)

ToolTweak: An Attack on Tool Selection in LLM-based Agents
por: Sneh, Jonathan, et al.
Publicado: (2025)

AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use
por: Yang, Chenglin
Publicado: (2026)

VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit
por: Lin, Junda, et al.
Publicado: (2026)

Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment
por: Xie, Yuchong, et al.
Publicado: (2025)

aCAPTCHA: Verifying That an Entity Is a Capable Agent via Asymmetric Hardness
por: Xu, Zuyao, et al.
Publicado: (2026)

MalURLBench: A Benchmark Evaluating Agents' Vulnerabilities When Processing Web URLs
por: Kong, Dezhang, et al.
Publicado: (2026)

Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation
por: Qiao, Yuxuan, et al.
Publicado: (2025)

LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring
por: Li, Chloe, et al.
Publicado: (2025)

SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
por: Liu, Zhe, et al.
Publicado: (2026)

Atomicity for Agents: Exposing, Exploiting, and Mitigating TOCTOU Vulnerabilities in Browser-Use Agents
por: Jiang, Linxi, et al.
Publicado: (2026)

Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction
por: Wang, Hongtao, et al.
Publicado: (2026)

Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling
por: Wang, Ziwei, et al.
Publicado: (2026)

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

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents
por: Probst, Benjamin, et al.
Publicado: (2026)

RepliBench: Evaluating the Autonomous Replication Capabilities of Language Model Agents
por: Black, Sid, et al.
Publicado: (2025)

Towards Safe and Honest AI Agents with Neural Self-Other Overlap
por: Carauleanu, Marc, et al.
Publicado: (2024)

BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models
por: Liu, Shuaitong, et al.
Publicado: (2025)

Jailbreaking Large Language Models through Iterative Tool-Disguised Attacks via Reinforcement Learning
por: Wang, Zhaoqi, et al.
Publicado: (2026)

PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities
por: Liu, Zicheng, et al.
Publicado: (2025)

PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification
por: Li, Hongwei, et al.
Publicado: (2025)

RECUR: Resource Exhaustion Attack via Recursive-Entropy Guided Counterfactual Utilization and Reflection
por: Wang, Ziwei, et al.
Publicado: (2026)

AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery
por: Wang, Haowei, et al.
Publicado: (2025)

SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration
por: Pan, Yu, et al.
Publicado: (2026)

SafeSearch: Automated Red-Teaming of LLM-Based Search Agents
por: Dong, Jianshuo, et al.
Publicado: (2025)

Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use
por: Zhang, Wuyang, et al.
Publicado: (2026)

ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts
por: Luo, Yang, et al.
Publicado: (2026)

TrajAD: Trajectory Anomaly Detection for Trustworthy LLM Agents
por: Liu, Yibing, et al.
Publicado: (2026)

Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
por: Qu, Yubin, et al.
Publicado: (2026)

VulDetectBench: Evaluating the Deep Capability of Vulnerability Detection with Large Language Models
por: Liu, Yu, et al.
Publicado: (2024)

STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents
por: Li, Jing-Jing, et al.
Publicado: (2025)

Agent Capability Negotiation and Binding Protocol (ACNBP)
por: Huang, Ken, et al.
Publicado: (2025)