Copertina

WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cao, Tri, Chen, Yulin, Cao, Hieu, Li, Yibo, Le, Khoi, Nguyen, Thong, Li, Yuexin, He, Yufei, Liu, Yue, Yan, Shuicheng, Hooi, Bryan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents
di: Chen, Yulin, et al.
Pubblicazione: (2026)

VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents
di: Cao, Tri, et al.
Pubblicazione: (2025)

AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing
di: Li, Yuexin, et al.
Pubblicazione: (2026)

Defense Against Prompt Injection Attack by Leveraging Attack Techniques
di: Chen, Yulin, et al.
Pubblicazione: (2024)

TopicAttack: An Indirect Prompt Injection Attack via Topic Transition
di: Chen, Yulin, et al.
Pubblicazione: (2025)

Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods
di: Chen, Yulin, et al.
Pubblicazione: (2025)

PhishAgent: A Robust Multimodal Agent for Phishing Webpage Detection
di: Cao, Tri, et al.
Pubblicazione: (2024)

Can Indirect Prompt Injection Attacks Be Detected and Removed?
di: Chen, Yulin, et al.
Pubblicazione: (2025)

Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models
di: Cao, Tri, et al.
Pubblicazione: (2026)

Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models
di: Sui, Yuan, et al.
Pubblicazione: (2025)

Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
di: Li, Yibo, et al.
Pubblicazione: (2026)

Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction
di: Chen, Yulin, et al.
Pubblicazione: (2025)

EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems
di: He, Yufei, et al.
Pubblicazione: (2025)

Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?
di: He, Yufei, et al.
Pubblicazione: (2025)

Words or Vision: Do Vision-Language Models Have Blind Faith in Text?
di: Deng, Ailin, et al.
Pubblicazione: (2025)

Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections
di: Yang, Xianglin, et al.
Pubblicazione: (2026)

Diffusion-Guided Adversarial Perturbation Injection for Generalizable Defense Against Facial Manipulations
di: Li, Yue, et al.
Pubblicazione: (2026)

TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering
di: Sui, Yuan, et al.
Pubblicazione: (2026)

When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift
di: Le, Khoi, et al.
Pubblicazione: (2026)

AegisAgent: An Autonomous Defense Agent Against Prompt Injection Attacks in LLM-HARs
di: Wang, Yihan, et al.
Pubblicazione: (2025)

Towards Realistic Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions
di: Guo, Qianyun, et al.
Pubblicazione: (2026)

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
di: Zhu, Kaijie, et al.
Pubblicazione: (2025)

A Multi-Agent LLM Defense Pipeline Against Prompt Injection Attacks
di: Hossain, S M Asif, et al.
Pubblicazione: (2025)

WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
di: Evtimov, Ivan, et al.
Pubblicazione: (2025)

KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection
di: Li, Yuexin, et al.
Pubblicazione: (2024)

Agent Privilege Separation in OpenClaw: A Structural Defense Against Prompt Injection
di: Cheng, Darren, et al.
Pubblicazione: (2026)

Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
di: Zhan, Qiusi, et al.
Pubblicazione: (2025)

Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses
di: Nguyen, Thanh, et al.
Pubblicazione: (2024)

BaThe: Defense against the Jailbreak Attack in Multimodal Large Language Models by Treating Harmful Instruction as Backdoor Trigger
di: Chen, Yulin, et al.
Pubblicazione: (2024)

Tit-for-Tat: Safeguarding Large Vision-Language Models Against Jailbreak Attacks via Adversarial Defense
di: Hao, Shuyang, et al.
Pubblicazione: (2025)

Defending Against Prompt Injection With a Few DefensiveTokens
di: Chen, Sizhe, et al.
Pubblicazione: (2025)

Beyond the Benchmark: Innovative Defenses Against Prompt Injection Attacks
di: Shaheer, Safwan, et al.
Pubblicazione: (2025)

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
di: An, Hengyu, et al.
Pubblicazione: (2025)

Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies
di: Lou, Zhanzhi, et al.
Pubblicazione: (2026)

APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents
di: Li, Yibo, et al.
Pubblicazione: (2026)

Fake News in Sheep's Clothing: Robust Fake News Detection Against LLM-Empowered Style Attacks
di: Wu, Jiaying, et al.
Pubblicazione: (2023)

ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction
di: Wang, Che, et al.
Pubblicazione: (2026)

WebInject: Prompt Injection Attack to Web Agents
di: Wang, Xilong, et al.
Pubblicazione: (2025)

EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning
di: He, Yufei, et al.
Pubblicazione: (2026)

Defense Against Indirect Prompt Injection via Tool Result Parsing
di: Yu, Qiang, et al.
Pubblicazione: (2026)