:: Library Catalog

Image de couverture de livre

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jiang, Xiaochong, Yang, Shiqi, Li, Ziwei, Liu, Lifei, Yu, Haoran, Liu, Yichen
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security Artificial Intelligence
Accès en ligne:	https://arxiv.org/abs/2605.26542
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SOK: A Taxonomy of Attack Vectors and Defense Strategies for Agentic Supply Chain Runtime
par: Jiang, Xiaochong, et autres
Publié: (2026)

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems
par: Wang, Su, et autres
Publié: (2026)

CapSeal: Capability-Sealed Secret Mediation for Secure Agent Execution
par: Jin, Shutong, et autres
Publié: (2026)

SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents
par: Liang, Siyuan, et autres
Publié: (2025)

SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
par: Yin, Sheng, et autres
Publié: (2024)

The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck
par: Fan, Linfeng, et autres
Publié: (2026)

Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents
par: Zhou, Kaiyu, et autres
Publié: (2026)

SafeHarness: Lifecycle-Integrated Security Architecture for LLM-based Agent Deployment
par: Lin, Xixun, et autres
Publié: (2026)

Evaluating Privilege Usage of Agents with Real-World Tools
par: Zhang, Quan, et autres
Publié: (2026)

ToolTweak: An Attack on Tool Selection in LLM-based Agents
par: Sneh, Jonathan, et autres
Publié: (2025)

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

VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit
par: Lin, Junda, et autres
Publié: (2026)

Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment
par: Xie, Yuchong, et autres
Publié: (2025)

aCAPTCHA: Verifying That an Entity Is a Capable Agent via Asymmetric Hardness
par: Xu, Zuyao, et autres
Publié: (2026)

MalURLBench: A Benchmark Evaluating Agents' Vulnerabilities When Processing Web URLs
par: Kong, Dezhang, et autres
Publié: (2026)

Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation
par: Qiao, Yuxuan, et autres
Publié: (2025)

LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring
par: Li, Chloe, et autres
Publié: (2025)

SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
par: Liu, Zhe, et autres
Publié: (2026)

Atomicity for Agents: Exposing, Exploiting, and Mitigating TOCTOU Vulnerabilities in Browser-Use Agents
par: Jiang, Linxi, et autres
Publié: (2026)

Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction
par: Wang, Hongtao, et autres
Publié: (2026)

Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling
par: Wang, Ziwei, et autres
Publié: (2026)

ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents
par: Lee, Seunghyun, et autres
Publié: (2026)

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents
par: Probst, Benjamin, et autres
Publié: (2026)

RepliBench: Evaluating the Autonomous Replication Capabilities of Language Model Agents
par: Black, Sid, et autres
Publié: (2025)

Towards Safe and Honest AI Agents with Neural Self-Other Overlap
par: Carauleanu, Marc, et autres
Publié: (2024)

BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models
par: Liu, Shuaitong, et autres
Publié: (2025)

Jailbreaking Large Language Models through Iterative Tool-Disguised Attacks via Reinforcement Learning
par: Wang, Zhaoqi, et autres
Publié: (2026)

PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities
par: Liu, Zicheng, et autres
Publié: (2025)

PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification
par: Li, Hongwei, et autres
Publié: (2025)

RECUR: Resource Exhaustion Attack via Recursive-Entropy Guided Counterfactual Utilization and Reflection
par: Wang, Ziwei, et autres
Publié: (2026)

AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery
par: Wang, Haowei, et autres
Publié: (2025)

SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration
par: Pan, Yu, et autres
Publié: (2026)

SafeSearch: Automated Red-Teaming of LLM-Based Search Agents
par: Dong, Jianshuo, et autres
Publié: (2025)

Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use
par: Zhang, Wuyang, et autres
Publié: (2026)

ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts
par: Luo, Yang, et autres
Publié: (2026)

TrajAD: Trajectory Anomaly Detection for Trustworthy LLM Agents
par: Liu, Yibing, et autres
Publié: (2026)

Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
par: Qu, Yubin, et autres
Publié: (2026)

VulDetectBench: Evaluating the Deep Capability of Vulnerability Detection with Large Language Models
par: Liu, Yu, et autres
Publié: (2024)

STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents
par: Li, Jing-Jing, et autres
Publié: (2025)

Agent Capability Negotiation and Binding Protocol (ACNBP)
par: Huang, Ken, et autres
Publié: (2025)