Image de couverture de livre

Unveiling the Security Risks of Federated Learning in the Wild: From Research to Practice

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Jiahao, Zhao, Zhiming, Pu, Yuwen, Zhou, Chunyi, Feng, Zhou, Li, Songze, Ji, Shouling
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Rethinking the Vulnerabilities of Face Recognition Systems:From a Practical Perspective
par: Chen, Jiahao, et autres
Publié: (2024)

Mellivora Capensis: A Backdoor-Free Training Framework on the Poisoned Dataset without Auxiliary Data
par: Pu, Yuwen, et autres
Publié: (2024)

FreeTalk:A plug-and-play and black-box defense against speech synthesis attacks
par: Pu, Yuwen, et autres
Publié: (2025)

Dullahan: Stealthy Backdoor Attack against Without-Label-Sharing Split Learning
par: Pu, Yuwen, et autres
Publié: (2024)

CAMH: Advancing Model Hijacking Attack in Machine Learning
par: He, Xing, et autres
Publié: (2024)

Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents
par: Chen, Jiahao, et autres
Publié: (2026)

Enhancing Adversarial Transferability with Adversarial Weight Tuning
par: Chen, Jiahao, et autres
Publié: (2024)

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks
par: Feng, Zhou, et autres
Publié: (2025)

Auditing M-LLMs for Privacy Risks: A Synthetic Benchmark and Evaluation Framework
par: Li, Junhao, et autres
Publié: (2025)

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning
par: Ma, Oubo, et autres
Publié: (2025)

LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing
par: Chen, Jiahao, et autres
Publié: (2025)

Hijack Vertical Federated Learning Models As One Party
par: Qiu, Pengyu, et autres
Publié: (2022)

ReCIT: Reconstructing Full Private Data from Gradient in Parameter-Efficient Fine-Tuning of Large Language Models
par: Xie, Jin, et autres
Publié: (2025)

Understanding the Security Risks of Decentralized Exchanges by Uncovering Unfair Trades in the Wild
par: Chen, Jiaqi, et autres
Publié: (2024)

TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning
par: Zhang, Mingxuan, et autres
Publié: (2025)

Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning
par: Ma, Oubo, et autres
Publié: (2026)

Attributing and Exploiting Safety Vectors through Global Optimization in Large Language Models
par: Chu, Fengheng, et autres
Publié: (2026)

BackdoorIndicator: Leveraging OOD Data for Proactive Backdoor Detection in Federated Learning
par: Li, Songze, et autres
Publié: (2024)

A Wolf in Sheep's Clothing: Practical Black-box Adversarial Attacks for Evading Learning-based Windows Malware Detection in the Wild
par: Ling, Xiang, et autres
Publié: (2024)

Privacy-preserving Prompt Personalization in Federated Learning for Multimodal Large Language Models
par: Hou, Sizai, et autres
Publié: (2025)

Towards Scalable and Interpretable Mobile App Risk Analysis via Large Language Models
par: Yang, Yu, et autres
Publié: (2025)

CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents
par: Ba, Lei, et autres
Publié: (2026)

Decaf: Data Distribution Decompose Attack against Federated Learning
par: Dai, Zhiyang, et autres
Publié: (2024)

SecurePay: Enabling Secure and Fast Payment Processing for Platform Economy
par: Lin, Junru, et autres
Publié: (2025)

CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models
par: Zeng, Rui, et autres
Publié: (2024)

OmniLytics+: A Secure, Efficient, and Affordable Blockchain Data Market for Machine Learning through Off-Chain Processing
par: Li, Songze, et autres
Publié: (2024)

LLMs Cannot Reliably Judge (Yet?): A Comprehensive Assessment on the Robustness of LLM-as-a-Judge
par: Li, Songze, et autres
Publié: (2025)

Watch the Watcher! Backdoor Attacks on Security-Enhancing Diffusion Models
par: Li, Changjiang, et autres
Publié: (2024)

PriRoAgg: Achieving Robust Model Aggregation with Minimum Privacy Leakage for Federated Learning
par: Hou, Sizai, et autres
Publié: (2024)

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
par: An, Hengyu, et autres
Publié: (2025)

"No Matter What You Do": Purifying GNN Models via Backdoor Unlearning
par: Zhang, Jiale, et autres
Publié: (2024)

Unveiling the Landscape of LLM Deployment in the Wild: An Empirical Study
par: Hou, Xinyi, et autres
Publié: (2025)

Security Analysis of Ponzi Schemes in Ethereum Smart Contracts
par: Zhang, Chunyi, et autres
Publié: (2025)

On the Security Risks of ML-based Malware Detection Systems: A Survey
par: He, Ping, et autres
Publié: (2025)

Port Forwarding Services Are Forwarding Security Risks
par: Wang, Haoyuan, et autres
Publié: (2024)

A Comprehensive Evaluation and Practice of System Penetration Testing
par: Zhang, Chunyi, et autres
Publié: (2025)

SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems
par: Ma, Oubo, et autres
Publié: (2024)

Arbitrary-Threshold Fully Homomorphic Encryption with Lower Complexity
par: Chang, Yijia, et autres
Publié: (2025)

Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit
par: Yao, Duanyi, et autres
Publié: (2024)

URVFL: Undetectable Data Reconstruction Attack on Vertical Federated Learning
par: Yao, Duanyi, et autres
Publié: (2024)