Copertina

GhostEI-Bench: Do Mobile Agents Resilience to Environmental Injection in Dynamic On-Device Environments?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Chiyu, Song, Xinhao, Chai, Yunkai, Yao, Yang, Zhao, Haodong, Li, Lijun, Li, Jie, Teng, Yan, Liu, Gongshen, Wang, Yingchun
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Revisiting Backdoor Threat in Federated Instruction Tuning from a Signal Aggregation Perspective
di: Zhao, Haodong, et al.
Pubblicazione: (2026)

Environmental Injection Attacks against GUI Agents in Realistic Dynamic Environments
di: Zhang, Yitong, et al.
Pubblicazione: (2025)

UOR: Universal Backdoor Attacks on Pre-trained Language Models
di: Du, Wei, et al.
Pubblicazione: (2023)

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models
di: Zhao, Tianhang, et al.
Pubblicazione: (2025)

A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network
di: Zhao, Haodong, et al.
Pubblicazione: (2023)

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

Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review
di: Cheng, Pengzhou, et al.
Pubblicazione: (2023)

AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
di: Debenedetti, Edoardo, et al.
Pubblicazione: (2024)

SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer
di: Cheng, Pengzhou, et al.
Pubblicazione: (2024)

FedRS-Bench: Realistic Federated Learning Datasets and Benchmarks in Remote Sensing
di: Zhao, Haodong, et al.
Pubblicazione: (2025)

Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents
di: Cai, Yuandao, et al.
Pubblicazione: (2026)

Physical and Software Based Fault Injection Attacks Against TEEs in Mobile Devices: A Systemisation of Knowledge
di: Joy, Aaron, et al.
Pubblicazione: (2024)

WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents
di: Liu, Yinuo, et al.
Pubblicazione: (2025)

MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content
di: Guo, Ruoqi, et al.
Pubblicazione: (2026)

LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents
di: Yan, Zihe, et al.
Pubblicazione: (2025)

Who Grants the Agent Power? Defending Against Instruction Injection via Task-Centric Access Control
di: Cai, Yifeng, et al.
Pubblicazione: (2025)

Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack
di: Wang, Hao, et al.
Pubblicazione: (2026)

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

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
di: Chen, Yunhao, et al.
Pubblicazione: (2025)

AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations
di: He, Yu, et al.
Pubblicazione: (2026)

LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments
di: Zhang, Chiyu, et al.
Pubblicazione: (2026)

EmbTracker: Traceable Black-box Watermarking for Federated Language Models
di: Zhao, Haodong, et al.
Pubblicazione: (2026)

NSmark: Null Space Based Black-box Watermarking Defense Framework for Language Models
di: Zhao, Haodong, et al.
Pubblicazione: (2024)

HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?
di: Jiang, Yukun, et al.
Pubblicazione: (2026)

Hunting the Ghost: Towards Automatic Mining of IoT Hidden Services
di: Dong, Shuaike, et al.
Pubblicazione: (2025)

AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents
di: Zhang, Yixiang, et al.
Pubblicazione: (2026)

MKF-ADS: Multi-Knowledge Fusion Based Self-supervised Anomaly Detection System for Control Area Network
di: Cheng, Pengzhou, et al.
Pubblicazione: (2024)

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

OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs
di: Wang, Xin, et al.
Pubblicazione: (2026)

Ghost in the Transformer: Detecting Model Reuse with Invariant Spectral Signatures
di: Wang, Suqing, et al.
Pubblicazione: (2025)

Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection
di: Miao, Ziqi, et al.
Pubblicazione: (2025)

ProtegoFed: Backdoor-Free Federated Instruction Tuning with Interspersed Poisoned Data
di: Zhao, Haodong, et al.
Pubblicazione: (2026)

The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis
di: Wang, Peiran, et al.
Pubblicazione: (2026)

ObliInjection: Order-Oblivious Prompt Injection Attack to LLM Agents with Multi-source Data
di: Wang, Reachal, et al.
Pubblicazione: (2025)

SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents
di: Feng, Xinshun, et al.
Pubblicazione: (2026)

AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents
di: Li, Yanjie, et al.
Pubblicazione: (2025)

StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data
di: Wang, Yixu, et al.
Pubblicazione: (2025)

Collaborative Shadows: Distributed Backdoor Attacks in LLM-Based Multi-Agent Systems
di: Zhu, Pengyu, et al.
Pubblicazione: (2025)

DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents
di: Li, Hao, et al.
Pubblicazione: (2025)

Multimodal Instruction Disassembly with Covariate Shift Adaptation and Real-time Implementation
di: Bai, Yunkai, et al.
Pubblicazione: (2024)