Image de couverture de livre

AgentMark: Utility-Preserving Behavioral Watermarking for Agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Huang, Kaibo, Tan, Jin, Wei, Yukun, Li, Wanling, Zhang, Zipei, Tian, Hui, Yang, Zhongliang, Zhou, Linna
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ACF: A Collaborative Framework for Agent Covert Communication under Cognitive Asymmetry
par: Wu, Wansheng, et autres
Publié: (2026)

Agent Guide: A Simple Agent Behavioral Watermarking Framework
par: Huang, Kaibo, et autres
Publié: (2025)

GSDFuse: Capturing Cognitive Inconsistencies from Multi-Dimensional Weak Signals in Social Media Steganalysis
par: Huang, Kaibo, et autres
Publié: (2025)

Whispering Agents: An Event-driven Covert Communication Protocol For the Internet of Agents
par: Huang, Kaibo, et autres
Publié: (2025)

Sequential Behavioral Watermarking for LLM Agents
par: An, Hyeseon, et autres
Publié: (2026)

ChainMarks: Securing DNN Watermark with Cryptographic Chain
par: Choi, Brian, et autres
Publié: (2025)

TokenMark: A Modality-Agnostic Watermark for Pre-trained Transformers
par: Xu, Hengyuan, et autres
Publié: (2024)

MirrorMark: Generalizable Mirrored Sampling for Multi-bit LLM Watermarking
par: Jiang, Ya, et autres
Publié: (2026)

InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenance
par: Xu, Rui, et autres
Publié: (2024)

SkillTester: Benchmarking Utility and Security of Agent Skills
par: Wang, Leye, et autres
Publié: (2026)

Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code
par: Kim, Jungin, et autres
Publié: (2025)

HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?
par: Jiang, Yukun, et autres
Publié: (2026)

OptMark: Robust Multi-bit Diffusion Watermarking via Inference Time Optimization
par: Xing, Jiazheng, et autres
Publié: (2025)

Privacy-Aware RAG: Secure and Isolated Knowledge Retrieval
par: Zhou, Pengcheng, et autres
Publié: (2025)

Provably Secure Retrieval-Augmented Generation
par: Zhou, Pengcheng, et autres
Publié: (2025)

Blind PRNG Hijacking: An Undetectable Integrity-Preserving Attack Against LLM Watermarking
par: You, Ziyang, et autres
Publié: (2026)

SplitAgent: A Privacy-Preserving Distributed Architecture for Enterprise-Cloud Agent Collaboration
par: She, Jianshu
Publié: (2026)

A Comparative Evaluation of AI Agent Security Guardrails
par: Li, Qi, et autres
Publié: (2026)

Mark My Words: Analyzing and Evaluating Language Model Watermarks
par: Piet, Julien, et autres
Publié: (2023)

Invariant-based Robust Weights Watermark for Large Language Models
par: Guo, Qingxiao, et autres
Publié: (2025)

Protecting Your Voice: Temporal-aware Robust Watermarking
par: Li, Yue, et autres
Publié: (2025)

Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections
par: Yang, Xianglin, et autres
Publié: (2026)

AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills
par: Zhuang, Haomin, et autres
Publié: (2026)

Hide&Seek: Remove Image Watermarks with Negligible Cost via Pixel-wise Reconstruction
par: Chen, Huajie, et autres
Publié: (2026)

LATTICE: Evaluating Decision Support Utility of Crypto Agents
par: Chan, Aaron, et autres
Publié: (2026)

AgentRAE: Remote Action Execution through Notification-based Visual Backdoors against Screenshots-based Mobile GUI Agents
par: Luo, Yutao, et autres
Publié: (2026)

PentestJudge: Judging Agent Behavior Against Operational Requirements
par: Caldwell, Shane, et autres
Publié: (2025)

AI-Governed Agent Architecture for Web-Trustworthy Tokenization of Alternative Assets
par: Borjigin, Ailiya, et autres
Publié: (2025)

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

AESP: A Human-Sovereign Economic Protocol for AI Agents with Privacy-Preserving Settlement
par: Wang, Jian Sheng
Publié: (2026)

Neural Honeytrace: Plug&Play Watermarking Framework against Model Extraction Attacks
par: Xu, Yixiao, et autres
Publié: (2025)

Dynamic Risk Assessments for Offensive Cybersecurity Agents
par: Wei, Boyi, et autres
Publié: (2025)

MarkTune: Improving the Quality-Detectability Trade-off in Open-Weight LLM Watermarking
par: Zhao, Yizhou, et autres
Publié: (2025)

FreeMark: A Non-Invasive White-Box Watermarking for Deep Neural Networks
par: Chen, Yuzhang, et autres
Publié: (2024)

Zero-Knowledge Audit for Internet of Agents: Privacy-Preserving Communication Verification with Model Context Protocol
par: Jing, Guanlin, et autres
Publié: (2025)

RobWE: Robust Watermark Embedding for Personalized Federated Learning Model Ownership Protection
par: Xu, Yang, et autres
Publié: (2024)

Enforcing Benign Trajectories: A Behavioral Firewall for Structured-Workflow AI Agents
par: Dang, Hung
Publié: (2026)

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
par: Feng, Yunhao, et autres
Publié: (2026)

Multi-Designated Detector Watermarking for Language Models
par: Huang, Zhengan, et autres
Publié: (2024)

Vaporizer: Breaking Watermarking Schemes for Large Language Model Outputs
par: Ng, Jonathan Hong Jin, et autres
Publié: (2026)