Cover Image

BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhan, Qiusi, Ha, Hyeonjeong, Yang, Rui, Xu, Sirui, Chen, Hanyang, Gui, Liang-Yan, Wang, Yu-Xiong, Zhang, Huan, Ji, Heng, Kang, Daniel
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence 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

MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks
by: Ha, Hyeonjeong, et al.
Published: (2025)

InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
by: Zhan, Qiusi, et al.
Published: (2024)

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

EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
by: Yang, Rui, et al.
Published: (2025)

BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
by: Li, Juncheng, et al.
Published: (2025)

ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents
by: Wang, Yichen, et al.
Published: (2025)

SafeSearch: Do Not Trade Safety for Utility in LLM Search Agents
by: Zhan, Qiusi, et al.
Published: (2025)

TrojVLM: Backdoor Attack Against Vision Language Models
by: Lyu, Weimin, et al.
Published: (2024)

Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers
by: Wang, Jiancheng, et al.
Published: (2026)

Backdoor Attack with Sparse and Invisible Trigger
by: Gao, Yinghua, et al.
Published: (2023)

BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers
by: Xue, Jiaqi, et al.
Published: (2024)

Mutual Information guided Visual Contrastive Learning
by: Chen, Hanyang, et al.
Published: (2025)

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

Backdoor Attacks on Dense Retrieval via Public and Unintentional Triggers
by: Long, Quanyu, et al.
Published: (2024)

Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger
by: Zhu, Mingyan, et al.
Published: (2023)

Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models
by: Zhao, Shuai, et al.
Published: (2023)

MoReact: Generating Reactive Motion from Textual Descriptions
by: Xu, Xiyan, et al.
Published: (2025)

Removing the Trigger, Not the Backdoor: Alternative Triggers and Latent Backdoors
by: Abad, Gorka, et al.
Published: (2026)

Removing RLHF Protections in GPT-4 via Fine-Tuning
by: Zhan, Qiusi, et al.
Published: (2023)

BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents
by: Feng, Yunhao, et al.
Published: (2026)

InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction
by: Xu, Sirui, et al.
Published: (2024)

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
by: Liang, Siyuan, et al.
Published: (2023)

BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP
by: Bai, Jiawang, et al.
Published: (2023)

Twin Trigger Generative Networks for Backdoor Attacks against Object Detection
by: Li, Zhiying, et al.
Published: (2024)

VisualTrap: A Stealthy Backdoor Attack on GUI Agents via Visual Grounding Manipulation
by: Ye, Ziang, et al.
Published: (2025)

Backdooring Self-Supervised Contrastive Learning by Noisy Alignment
by: Chen, Tuo, et al.
Published: (2025)

Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers
by: Wei, Jiali, et al.
Published: (2026)

Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive Triggers
by: Huang, Binxiao, et al.
Published: (2024)

Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers
by: Wang, Ruotong, et al.
Published: (2023)

Low-Frequency Black-Box Backdoor Attack via Evolutionary Algorithm
by: Qiao, Yanqi, et al.
Published: (2024)

CPPO: Contrastive Perception Policy Optimization for VLM Agents
by: Rezaei, Ahmad, et al.
Published: (2026)

InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions
by: Xu, Sirui, et al.
Published: (2025)

PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding
by: Blume, Ansel, et al.
Published: (2025)

VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models
by: Liang, Jiawei, et al.
Published: (2024)

IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks
by: Lu, Xiaoya, et al.
Published: (2025)

ParallelVLM: Lossless Video-LLM Acceleration with Visual Alignment Aware Parallel Speculative Decoding
by: Kong, Quan, et al.
Published: (2026)

RoboStressBench: Benchmarking VLM Robustness to Physical Visual Stress in Embodied Scenes
by: Wu, Leyi, et al.
Published: (2026)

MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs
by: Wen, Rui, et al.
Published: (2026)

BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning
by: Yang, Ziqing, et al.
Published: (2026)

Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models
by: Liu, Zhaoyi, et al.
Published: (2025)