Cover Image

SlowBA: An efficiency backdoor attack towards VLM-based GUI agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Junxian, Lan, Tu, Tan, Haozhen, Meng, Yan, Zhu, Haojin
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Computation and Language Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

IAG: Input-aware Backdoor Attack on VLM-based Visual Grounding
by: Li, Junxian, et al.
Published: (2025)

Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection
by: Yang, Wenkui, et al.
Published: (2026)

CAT: Concept-level backdoor ATtacks for Concept Bottleneck Models
by: Lai, Songning, et al.
Published: (2024)

Assessing biomedical knowledge robustness in large language models by query-efficient sampling attacks
by: Xian, R. Patrick, et al.
Published: (2024)

DLP: towards active defense against backdoor attacks with decoupled learning process
by: Ying, Zonghao, et al.
Published: (2024)

TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
by: He, Xuanli, et al.
Published: (2024)

Analysis and prevention of AI-based phishing email attacks
by: Eze, Chibuike Samuel, et al.
Published: (2024)

Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks
by: Yi, Xin, et al.
Published: (2025)

Bodhi VLM: Privacy-Alignment Modeling for Hierarchical Visual Representations in Vision Backbones and VLM Encoders via Bottom-Up and Top-Down Feature Search
by: Ma, Bo, et al.
Published: (2026)

Trading Devil: Robust backdoor attack via Stochastic investment models and Bayesian approach
by: Mengara, Orson
Published: (2024)

Trojan's Whisper: Stealthy Manipulation of OpenClaw through Injected Bootstrapped Guidance
by: Liu, Fazhong, et al.
Published: (2026)

EO-VLM: VLM-Guided Energy Overload Attacks on Vision Models
by: Seo, Minjae, et al.
Published: (2025)

Self-adaptive Dataset Construction for Real-World Multimodal Safety Scenarios
by: Qu, Jingen, et al.
Published: (2025)

BSPA: Exploring Black-box Stealthy Prompt Attacks against Image Generators
by: Tian, Yu, et al.
Published: (2024)

Toward a Human-Centered Evaluation Framework for Trustworthy LLM-Powered GUI Agents
by: Chen, Chaoran, et al.
Published: (2025)

The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections
by: Chen, Chaoran, et al.
Published: (2025)

Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector
by: Huang, Youcheng, et al.
Published: (2024)

BodhiPromptShield: Pre-Inference Prompt Mediation for Suppressing Privacy Propagation in LLM/VLM Agents
by: Ma, Bo, et al.
Published: (2026)

Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs
by: Upadhayay, Bibek, et al.
Published: (2024)

Good Parenting is all you need -- Multi-agentic LLM Hallucination Mitigation
by: Kwartler, Ted, et al.
Published: (2024)

Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM
by: Yang, Xikang, et al.
Published: (2024)

BAIT: Boundary-Guided Disclosure Escalation via Self-Conditioned Reasoning
by: Luo, Xuan, et al.
Published: (2026)

Learning diverse attacks on large language models for robust red-teaming and safety tuning
by: Lee, Seanie, et al.
Published: (2024)

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

A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness
by: Luo, Xuan, et al.
Published: (2025)

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

ScaleOT: Privacy-utility-scalable Offsite-tuning with Dynamic LayerReplace and Selective Rank Compression
by: Yao, Kai, et al.
Published: (2024)

SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts
by: Xin, Yuan, et al.
Published: (2026)

Iteratively Prompting Multimodal LLMs to Reproduce Natural and AI-Generated Images
by: Naseh, Ali, et al.
Published: (2024)

Image-Based Geolocation Using Large Vision-Language Models
by: Liu, Yi, et al.
Published: (2024)

MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance
by: Pi, Renjie, et al.
Published: (2024)

Privacy-Preserving Federated Learning with Verifiable Fairness Guarantees
by: Ali, Mohammed Himayath, et al.
Published: (2026)

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

Generating Synthetic Data with Formal Privacy Guarantees: State of the Art and the Road Ahead
by: Schlegel, Viktor, et al.
Published: (2025)

Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models
by: Ding, Yi, et al.
Published: (2025)

Contextual Image Attack: How Visual Context Exposes Multimodal Safety Vulnerabilities
by: Xiong, Yuan, et al.
Published: (2025)

Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study
by: Lee, DongGeon, et al.
Published: (2025)

Doubly-Universal Adversarial Perturbations: Deceiving Vision-Language Models Across Both Images and Text with a Single Perturbation
by: Kim, Hee-Seon, et al.
Published: (2024)

Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory
by: Zhang, Ce, et al.
Published: (2026)

Prompt Injection attack against LLM-integrated Applications
by: Liu, Yi, et al.
Published: (2023)