Copertina

Evaluating the Robustness of Multimodal Agents Against Active Environmental Injection Attacks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Yurun, Hu, Xavier, Yin, Keting, Li, Juncheng, Zhang, Shengyu
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

HarmonyGuard: Toward Safety and Utility in Web Agents via Adaptive Policy Enhancement and Dual-Objective Optimization
di: Chen, Yurun, et al.
Pubblicazione: (2025)

SafePred: A Predictive Guardrail for Computer-Using Agents via World Models
di: Chen, Yurun, et al.
Pubblicazione: (2026)

Graph2Eval: Automatic Multimodal Task Generation for Agents via Knowledge Graphs
di: Chen, Yurun, et al.
Pubblicazione: (2025)

Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion
di: Lv, Zheqi, et al.
Pubblicazione: (2025)

World-Model-Augmented Web Agents with Action Correction
di: Shen, Zhouzhou, et al.
Pubblicazione: (2026)

EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage
di: Liao, Zeyi, et al.
Pubblicazione: (2024)

J&H: Evaluating the Robustness of Large Language Models Under Knowledge-Injection Attacks in Legal Domain
di: Hu, Yiran, et al.
Pubblicazione: (2025)

InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners
di: Liu, Yuhang, et al.
Pubblicazione: (2025)

Reinforce LLM Reasoning through Multi-Agent Reflection
di: Yuan, Yurun, et al.
Pubblicazione: (2025)

Robust LLM Unlearning Against Relearning Attacks: The Minor Components in Representations Matter
di: Xiao, Zeguan, et al.
Pubblicazione: (2026)

Defending Against Indirect Prompt Injection Attacks With Spotlighting
di: Hines, Keegan, et al.
Pubblicazione: (2024)

Robustness of Large Language Models Against Adversarial Attacks
di: Tao, Yiyi, et al.
Pubblicazione: (2024)

Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks
di: Mu, Lin, et al.
Pubblicazione: (2025)

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

Benchmarking Gaslighting Negation Attacks Against Multimodal Large Language Models
di: Zhu, Bin, et al.
Pubblicazione: (2025)

Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models
di: Yi, Jingwei, et al.
Pubblicazione: (2023)

Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation
di: Meng, Wenlong, et al.
Pubblicazione: (2025)

FormFactory: An Interactive Benchmarking Suite for Multimodal Form-Filling Agents
di: Li, Bobo, et al.
Pubblicazione: (2025)

Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategies
di: Xiong, Tao, et al.
Pubblicazione: (2025)

Camouflage is all you need: Evaluating and Enhancing Language Model Robustness Against Camouflage Adversarial Attacks
di: Huertas-García, Álvaro, et al.
Pubblicazione: (2024)

Is Your Prompt Safe? Investigating Prompt Injection Attacks Against Open-Source LLMs
di: Wang, Jiawen, et al.
Pubblicazione: (2025)

ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning
di: Wu, Juncheng, et al.
Pubblicazione: (2026)

Defense against Prompt Injection Attacks via Mixture of Encodings
di: Zhang, Ruiyi, et al.
Pubblicazione: (2025)

Cascaded Self-Evaluation Augmented Training for Lightweight Multimodal LLMs
di: Lv, Zheqi, et al.
Pubblicazione: (2025)

Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions
di: Ma, Xinbei, et al.
Pubblicazione: (2024)

Robust Multimodal Large Language Models Against Modality Conflict
di: Zhang, Zongmeng, et al.
Pubblicazione: (2025)

EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents
di: Cheng, Zhili, et al.
Pubblicazione: (2025)

ACIArena: Toward Unified Evaluation for Agent Cascading Injection
di: An, Hengyu, et al.
Pubblicazione: (2026)

OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use
di: Hu, Xueyu, et al.
Pubblicazione: (2025)

Prompt Injection Attacks in Defended Systems
di: Khomsky, Daniil, et al.
Pubblicazione: (2024)

Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study
di: Hou, Guanyu, et al.
Pubblicazione: (2025)

InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection
di: Liu, Yuhang, et al.
Pubblicazione: (2025)

Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents
di: Fujinuma, Yoshinari, et al.
Pubblicazione: (2026)

Dual-Modality Multi-Stage Adversarial Safety Training: Robustifying Multimodal Web Agents Against Cross-Modal Attacks
di: Liu, Haoyu, et al.
Pubblicazione: (2026)

Temperature Matters: Enhancing Watermark Robustness Against Paraphrasing Attacks
di: Idrissi, Badr Youbi, et al.
Pubblicazione: (2025)

Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
di: Qu, Yubin, et al.
Pubblicazione: (2026)

Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States
di: Yuan, Yurun, et al.
Pubblicazione: (2026)

Enhance Robustness of Language Models Against Variation Attack through Graph Integration
di: Xiong, Zi, et al.
Pubblicazione: (2024)

SOTOPIA-$Ω$: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agents
di: Zhang, Wenyuan, et al.
Pubblicazione: (2025)

Membership Inference Attacks Against In-Context Learning
di: Wen, Rui, et al.
Pubblicazione: (2024)