Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation
Authors: Wenkai Guo, Xuefeng Liu, Haolin Wang, Jianwei Niu, Shaojie Tang, Jing Yuan | Published: 2025-09-25
Poisoning
Not All Samples Are Equal: Quantifying Instance-level Difficulty in Targeted Data Poisoning
Authors: William Xu, Yiwei Lu, Yihan Wang, Matthew Y. R. Yang, Zuoqiu Liu, Gautam Kamath, Yaoliang Yu | Published: 2025-09-08
On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directions
Authors: Daniel M. Jimenez-Gutierrez, Yelizaveta Falkouskaya, Jose L. Hernandez-Ramos, Aris Anagnostopoulos, Ioannis Chatzigiannakis, Andrea Vitaletti | Published: 2025-08-19
Non-omniscient backdoor injection with a single poison sample: Proving the one-poison hypothesis for linear regression and linear classification
Authors: Thorsten Peinemann, Paula Arnold, Sebastian Berndt, Thomas Eisenbarth, Esfandiar Mohammadi | Published: 2025-08-07
Cascading and Proxy Membership Inference Attacks
Authors: Yuntao Du, Jiacheng Li, Yuetian Chen, Kaiyuan Zhang, Zhizhen Yuan, Hanshen Xiao, Bruno Ribeiro, Ninghui Li | Published: 2025-07-29
Byzantine Failures Harm the Generalization of Robust Distributed Learning Algorithms More Than Data Poisoning
Authors: Thomas Boudou, Batiste Le Bars, Nirupam Gupta, Aurélien Bellet | Published: 2025-06-22 | Updated: 2025-10-16
A Linear Approach to Data Poisoning
Authors: Diego Granziol, Donald Flynn | Published: 2025-05-21
One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
Authors: Zhiyuan Chang, Mingyang Li, Xiaojun Jia, Junjie Wang, Yuekai Huang, Ziyou Jiang, Yang Liu, Qing Wang | Published: 2025-05-15 | Updated: 2025-05-20
Toward Malicious Clients Detection in Federated Learning
Authors: Zhihao Dou, Jiaqi Wang, Wei Sun, Zhuqing Liu, Minghong Fang | Published: 2025-05-14
Analysis of the vulnerability of machine learning regression models to adversarial attacks using data from 5G wireless networks
Authors: Leonid Legashev, Artur Zhigalov, Denis Parfenov | Published: 2025-05-01