Image de couverture de livre

In-Browser LLM-Guided Fuzzing for Real-Time Prompt Injection Testing in Agentic AI Browsers

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Cohen, Avihay
Format:	Preprint
Publié:	2025
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

Client-Side Zero-Shot LLM Inference for Comprehensive In-Browser URL Analysis
par: Cohen, Avihay
Publié: (2025)

Browser Security Posture Analysis: A Client-Side Security Assessment Framework
par: Cohen, Avihay
Publié: (2025)

JavaSith: A Client-Side Framework for Analyzing Potentially Malicious Extensions in Browsers, VS Code, and NPM Packages
par: Cohen, Avihay
Publié: (2025)

BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents
par: Zhang, Kaiyuan, et autres
Publié: (2025)

The Cognitive Firewall:Securing Browser Based AI Agents Against Indirect Prompt Injection Via Hybrid Edge Cloud Defense
par: Lan, Qianlong, et autres
Publié: (2026)

PROMPTFUZZ: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMs
par: Yu, Jiahao, et autres
Publié: (2024)

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

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

Toward Trustworthy Agentic AI: A Multimodal Framework for Preventing Prompt Injection Attacks
par: Syed, Toqeer Ali, et autres
Publié: (2025)

Fingerprinting and Tracing Shadows: The Development and Impact of Browser Fingerprinting on Digital Privacy
par: Lawall, Alexander
Publié: (2024)

WAAA! Web Adversaries Against Agentic Browsers
par: Datta, Sohom, et autres
Publié: (2026)

Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces
par: Lugoloobi, William, et autres
Publié: (2026)

Hybrid Fuzzing with LLM-Guided Input Mutation and Semantic Feedback
par: Lin, Shiyin
Publié: (2025)

From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows
par: Ferrag, Mohamed Amine, et autres
Publié: (2025)

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt
par: Wang, Zhilong, et autres
Publié: (2025)

Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks
par: Pasquini, Dario, et autres
Publié: (2024)

AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs
par: Wang, Che, et autres
Publié: (2026)

Beyond the Request: Harnessing HTTP Response Headers for Cross-Browser Web Tracker Classification in an Imbalanced Setting
par: Rieder, Wolf, et autres
Publié: (2024)

Prompt Injection 2.0: Hybrid AI Threats
par: McHugh, Jeremy, et autres
Publié: (2025)

Securing AI Agents Against Prompt Injection Attacks
par: Ramakrishnan, Badrinath, et autres
Publié: (2025)

EchoLeak: The First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System
par: Reddy, Pavan, et autres
Publié: (2025)

Optimization-based Prompt Injection Attack to LLM-as-a-Judge
par: Shi, Jiawen, et autres
Publié: (2024)

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

RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage
par: Zhong, Peter Yong, et autres
Publié: (2025)

Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems
par: Chang, Hongyan, et autres
Publié: (2026)

Signed-Prompt: A New Approach to Prevent Prompt Injection Attacks Against LLM-Integrated Applications
par: Suo, Xuchen
Publié: (2024)

Bypassing Prompt Injection Detectors through Evasive Injections
par: Rahman, Md Jahedur, et autres
Publié: (2026)

PromptLocate: Localizing Prompt Injection Attacks
par: Jia, Yuqi, et autres
Publié: (2025)

How Not to Detect Prompt Injections with an LLM
par: Choudhary, Sarthak, et autres
Publié: (2025)

ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents
par: Sehwag, Udari Madhushani, et autres
Publié: (2026)

Privacy Practices of Browser Agents
par: Ukani, Alisha, et autres
Publié: (2025)

Defeating Prompt Injections by Design
par: Debenedetti, Edoardo, et autres
Publié: (2025)

When AI Meets the Web: Prompt Injection Risks in Third-Party AI Chatbot Plugins
par: Kaya, Yigitcan, et autres
Publié: (2025)

Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Prompts
par: Hasan, Md. Mehedi, et autres
Publié: (2025)

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
par: Zhu, Kaijie, et autres
Publié: (2025)

Locus: Agentic Predicate Synthesis for Directed Fuzzing
par: Zhu, Jie, et autres
Publié: (2025)

Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
par: Lee, Donghyun, et autres
Publié: (2024)

PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs
par: Gong, Xueluan, et autres
Publié: (2024)

LLM-Guided Prompt Evolution for Password Guessing
par: Mazin, Vladimir A., et autres
Publié: (2026)

Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks
par: Chen, Sizhe, et autres
Publié: (2025)