Copertina

Collaborative Shadows: Distributed Backdoor Attacks in LLM-Based Multi-Agent Systems

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhu, Pengyu, Li, Lijun, Lyu, Yaxing, Sun, Li, Su, Sen, Shao, Jing
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

Infighting in the Dark: Multi-Label Backdoor Attack in Federated Learning
di: Li, Ye, et al.
Pubblicazione: (2024)

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems
di: Wang, Liwen, et al.
Pubblicazione: (2025)

Real is not True: Backdoor Attacks Against Deepfake Detection
di: Sun, Hong, et al.
Pubblicazione: (2024)

HarmRLVR: Weaponizing Verifiable Rewards for Harmful LLM Alignment
di: Liu, Yuexiao, et al.
Pubblicazione: (2025)

Distributed Backdoor Attacks on Federated Graph Learning and Certified Defenses
di: Yang, Yuxin, et al.
Pubblicazione: (2024)

ShadowLogic: Backdoors in Any Whitebox LLM
di: Schulz, Kasimir, et al.
Pubblicazione: (2025)

ProvAgent: Threat Detection Based on Identity-Behavior Binding and Multi-Agent Collaborative Attack Investigation
di: Yan, Wenhao, et al.
Pubblicazione: (2026)

The Trust Paradox in LLM-Based Multi-Agent Systems: When Collaboration Becomes a Security Vulnerability
di: Xu, Zijie, et al.
Pubblicazione: (2025)

DSBA: Dynamic Stealthy Backdoor Attack with Collaborative Optimization in Self-Supervised Learning
di: Wang, Jiayao, et al.
Pubblicazione: (2026)

SSD: A State-based Stealthy Backdoor Attack For Navigation System in UAV Route Planning
di: Wang, Zhaoxuan, et al.
Pubblicazione: (2025)

Isolate Trigger: Detecting and Eliminating Adaptive Backdoor Attacks
di: Sun, Chengrui, et al.
Pubblicazione: (2025)

Attack by Yourself: Effective and Unnoticeable Multi-Category Graph Backdoor Attacks with Subgraph Triggers Pool
di: Li, Jiangtong, et al.
Pubblicazione: (2024)

Exploring Backdoor Attack and Defense for LLM-empowered Recommendations
di: Ning, Liangbo, et al.
Pubblicazione: (2025)

Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
di: Bai, Li, et al.
Pubblicazione: (2025)

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

Red-Teaming LLM Multi-Agent Systems via Communication Attacks
di: He, Pengfei, et al.
Pubblicazione: (2025)

Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
di: Chen, Xuan, et al.
Pubblicazione: (2025)

Backdoor Attack with Invisible Triggers Based on Model Architecture Modification
di: Ma, Yuan, et al.
Pubblicazione: (2024)

Task-Agnostic Detector for Insertion-Based Backdoor Attacks
di: Lyu, Weimin, et al.
Pubblicazione: (2024)

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

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

Stateful Agent Backdoor
di: Dai, Zhengchunmin, et al.
Pubblicazione: (2026)

Towards Effective, Stealthy, and Persistent Backdoor Attacks Targeting Graph Foundation Models
di: Luo, Jiayi, et al.
Pubblicazione: (2025)

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment
di: Li, Hao, et al.
Pubblicazione: (2025)

SPA: Towards More Stealth and Persistent Backdoor Attacks in Federated Learning
di: Zhu, Chengcheng, et al.
Pubblicazione: (2025)

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

M-to-N Backdoor Paradigm: A Multi-Trigger and Multi-Target Attack to Deep Learning Models
di: Hou, Linshan, et al.
Pubblicazione: (2022)

BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models
di: Yuan, Zenghui, et al.
Pubblicazione: (2025)

Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approach
di: Qi, Minfeng, et al.
Pubblicazione: (2025)

On the Out-of-Distribution Backdoor Attack for Federated Learning
di: Xu, Jiahao, et al.
Pubblicazione: (2025)

Concept-Guided Backdoor Attack on Vision Language Models
di: Shen, Haoyu, et al.
Pubblicazione: (2025)

Stealthy Targeted Backdoor Attacks against Image Captioning
di: Fan, Wenshu, et al.
Pubblicazione: (2024)

CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
di: Ning, Liang-bo, et al.
Pubblicazione: (2025)

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

Poisoning the Pixels: Revisiting Backdoor Attacks on Semantic Segmentation
di: Zhang, Guangsheng, et al.
Pubblicazione: (2026)

Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods
di: Chen, Yulin, et al.
Pubblicazione: (2025)

Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification
di: Wang, Xiaobao, et al.
Pubblicazione: (2025)