Image de couverture de livre

Cross-Modal Content Optimization for Steering Web Agent Preferences

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jiang, Tanqiu, Bai, Min, Pappas, Nikolaos, Qi, Yanjun, Swamy, Sandesh
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents
par: Zou, Wei, et autres
Publié: (2026)

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

MAGE: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory
par: Wang, Yuhui, et autres
Publié: (2026)

Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization
par: Lin, Zhixin, et autres
Publié: (2026)

RASA: Routing-Aware Safety Alignment for Mixture-of-Experts Models
par: Liang, Jiacheng, et autres
Publié: (2026)

Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation
par: Schwartz, Daniel, et autres
Publié: (2025)

WebTrap Park: An Automated Platform for Systematic Security Evaluation of Web Agents
par: Wu, Xinyi, et autres
Publié: (2026)

Mind the Web: The Security of Web Use Agents
par: Shapira, Avishag, et autres
Publié: (2025)

WIPI: A New Web Threat for LLM-Driven Web Agents
par: Wu, Fangzhou, et autres
Publié: (2024)

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
par: Jiang, Tanqiu, et autres
Publié: (2024)

Multi-Agent Penetration Testing AI for the Web
par: David, Isaac, et autres
Publié: (2025)

If Only My CGM Could Speak: A Privacy-Preserving Agent for Question Answering over Continuous Glucose Data
par: Cui, Yanjun, et autres
Publié: (2026)

DECEPTICON: How Dark Patterns Manipulate Web Agents
par: Cuvin, Phil, et autres
Publié: (2025)

AWE: Adaptive Agents for Dynamic Web Penetration Testing
par: Jaswal, Akshat Singh, et autres
Publié: (2026)

X-Guard: Multilingual Guard Agent for Content Moderation
par: Upadhayay, Bibek, et autres
Publié: (2025)

Don't Click That: Teaching Web Agents to Resist Deceptive Interfaces
par: Zhang, Yilin, et autres
Publié: (2026)

GraphRAG under Fire
par: Liang, Jiacheng, et autres
Publié: (2025)

Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models
par: Xiong, Chen, et autres
Publié: (2026)

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

WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
par: Evtimov, Ivan, et autres
Publié: (2025)

WebPII: Benchmarking Visual PII Detection for Computer-Use Agents
par: Zhao, Nathan
Publié: (2026)

WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections
par: Cao, Tri, et autres
Publié: (2026)

CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks
par: Zhang, Xu, et autres
Publié: (2025)

DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization
par: Tang, Wenxin, et autres
Publié: (2026)

WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation
par: Liu, Zhichao, et autres
Publié: (2026)

SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents
par: Du, Mengyao, et autres
Publié: (2026)

Autonomous Intelligent Agents for Natural-Language-Driven Web Execution with Integrated Security Assurance
par: Pasupuleti, Vinil, et autres
Publié: (2026)

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

An Application-Layer Multi-Modal Covert-Channel Reference Monitor for LLM Agent Egress
par: Metere, Alfredo
Publié: (2026)

Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree
par: Johnson, Sam, et autres
Publié: (2025)

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

MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks
par: Syros, Georgios, et autres
Publié: (2026)

Watermarking across Modalities for Content Tracing and Generative AI
par: Fernandez, Pierre
Publié: (2025)

Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion
par: Pramanik, Vishal, et autres
Publié: (2026)

WebWeaver: Breaking Topology Confidentiality in LLM Multi-Agent Systems with Stealthy Context-Based Inference
par: Xiong, Zixun, et autres
Publié: (2026)

When Bots Take the Bait: Exposing and Mitigating the Emerging Social Engineering Attack in Web Automation Agent
par: Wu, Xinyi, et autres
Publié: (2026)

ShallowJail: Steering Jailbreaks against Large Language Models
par: Liu, Shang, et autres
Publié: (2026)

Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study
par: Chen, Zhihao, et autres
Publié: (2026)

IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection
par: Chia-Pei, et autres
Publié: (2026)

WebSentinel: Detecting and Localizing Prompt Injection Attacks for Web Agents
par: Wang, Xilong, et autres
Publié: (2026)