Imagen de Portada

BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Feng, Yunhao, Li, Yige, Wu, Yutao, Tan, Yingshui, Guo, Yanming, Ding, Yifan, Zhai, Kun, Ma, Xingjun, Jiang, Yu-Gang
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
por: Feng, Yunhao, et al.
Publicado: (2026)

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
por: Feng, Yunhao, et al.
Publicado: (2026)

AutoBackdoor: Automating Backdoor Attacks via LLM Agents
por: Li, Yige, et al.
Publicado: (2025)

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

BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
por: Li, Yige, et al.
Publicado: (2024)

Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks
por: Li, Yige, et al.
Publicado: (2024)

Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models
por: Li, Yige, et al.
Publicado: (2024)

BraveGuard: From Open-World Threats to Safer Computer-Use Agents
por: Feng, Yunhao, et al.
Publicado: (2026)

AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models
por: Li, Jiayu, et al.
Publicado: (2025)

Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs
por: Li, Yige, et al.
Publicado: (2026)

DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
por: Zhu, Pengyu, et al.
Publicado: (2025)

End-to-End Anti-Backdoor Learning on Images and Time Series
por: Jiang, Yujing, et al.
Publicado: (2024)

Detecting Backdoor Samples in Contrastive Language Image Pretraining
por: Huang, Hanxun, et al.
Publicado: (2025)

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
por: Jiang, Peihai, et al.
Publicado: (2025)

BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents
por: Wang, Yifei, et al.
Publicado: (2024)

DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models
por: Xu, Zonghuan, et al.
Publicado: (2025)

HoneypotNet: Backdoor Attacks Against Model Extraction
por: Wang, Yixu, et al.
Publicado: (2025)

Compromising Embodied Agents with Contextual Backdoor Attacks
por: Liu, Aishan, et al.
Publicado: (2024)

Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs
por: Zheng, Xiang, et al.
Publicado: (2026)

PaperAsk: A Benchmark for Reliability Evaluation of LLMs in Paper Search and Reading
por: Wu, Yutao, et al.
Publicado: (2025)

Stateful Agent Backdoor
por: Dai, Zhengchunmin, et al.
Publicado: (2026)

Towards Unified Robustness Against Both Backdoor and Adversarial Attacks
por: Niu, Zhenxing, et al.
Publicado: (2024)

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

Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World
por: Yin, Wen, et al.
Publicado: (2024)

Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
por: Wei, Shaokui, et al.
Publicado: (2024)

Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias
por: Wu, Shangxi, et al.
Publicado: (2023)

Your Agent Can Defend Itself against Backdoor Attacks
por: Changjiang, Li, et al.
Publicado: (2025)

Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
por: Cui, Kaiyuan, et al.
Publicado: (2026)

AgentRAE: Remote Action Execution through Notification-based Visual Backdoors against Screenshots-based Mobile GUI Agents
por: Luo, Yutao, et al.
Publicado: (2026)

ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking
por: Wu, Yutao, et al.
Publicado: (2025)

VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models
por: Chou, Sheng-Yen, et al.
Publicado: (2023)

Is the Trigger Essential? A Feature-Based Triggerless Backdoor Attack in Vertical Federated Learning
por: Liu, Yige, et al.
Publicado: (2026)

Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
por: Yang, Wenkai, et al.
Publicado: (2024)

When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations
por: Ge, Huaizhi, et al.
Publicado: (2024)

Parasite: A Steganography-based Backdoor Attack Framework for Diffusion Models
por: Chen, Jiahao, et al.
Publicado: (2025)

Event Trojan: Asynchronous Event-based Backdoor Attacks
por: Wang, Ruofei, et al.
Publicado: (2024)

Data Free Backdoor Attacks
por: Cao, Bochuan, et al.
Publicado: (2024)

Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems
por: Jiao, Ruochen, et al.
Publicado: (2024)

Persistent Backdoor Attacks in Continual Learning
por: Guo, Zhen, et al.
Publicado: (2024)

Invisible Backdoor Attacks on Diffusion Models
por: Li, Sen, et al.
Publicado: (2024)