English
Related papers

Related papers: Improved Certified Defenses against Data Poisoning…

200 papers

Targeted data poisoning (TDP) aims to compromise the model's prediction on a specific (test) target by perturbing a small subset of training data. Existing work on TDP has focused on an overly ideal threat model in which the same image…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Zhizhen Chen , Zhengyu Zhao , Subrat Kishore Dutta , Chenhao Lin , Chao Shen , Xiao Zhang

Federated learning (FL) enables collaborative model training by aggregating local updates without requiring raw data sharing. However, prior studies have shown that servers can exploit gradient inversion to compromise user privacy or…

Cryptography and Security · Computer Science 2026-05-26 Yufei Zhou

Adversarial attacks significantly threaten the robustness of deep neural networks (DNNs). Despite the multiple defensive methods employed, they are nevertheless vulnerable to poison attacks, where attackers meddle with the initial training…

Machine Learning · Computer Science 2023-03-29 Bakary Badjie , José Cecílio , António Casimiro

Existing work in trustworthy machine learning primarily focuses on single-input adversarial perturbations. In many real-world attack scenarios, input-agnostic adversarial attacks, e.g. universal adversarial perturbations (UAPs), are much…

Machine Learning · Computer Science 2024-09-10 Changming Xu , Gagandeep Singh

Over-the-air federated learning (OTA-FL) improves communication efficiency by exploiting the superposition property of wireless channels, but this same property also creates a critical security vulnerability: the parameter server (PS)…

Cryptography and Security · Computer Science 2026-05-20 Xiaoyan Ma , Seohyun Lee , Taejoon Kim , Christopher G. Brinton

Data poisoning attacks are a potential threat to machine learning (ML) models, aiming to manipulate training datasets to disrupt their performance. Existing defenses are mostly designed to mitigate specific poisoning attacks or are aligned…

Cryptography and Security · Computer Science 2025-10-28 Anum Paracha , Junaid Arshad , Mohamed Ben Farah , Khalid Ismail

Federated learning enables collaborative model training across distributed clients, yet vanilla FL exposes client updates to the central server. Secure-aggregation schemes protect privacy against an honest-but-curious server, but existing…

Cryptography and Security · Computer Science 2026-05-14 Haaris Mehmood , Giorgos Tatsis , Dimitrios Alexopoulos , Karthikeyan Saravanan , Jie Xu , Anastasios Drosou , Mete Ozay

Federated Learning (FL) is a distributed machine learning diagram that enables multiple clients to collaboratively train a global model without sharing their private local data. However, FL systems are vulnerable to attacks that are…

Machine Learning · Computer Science 2024-08-20 Qilei Li , Ahmed M. Abdelmoniem

In the evolving landscape of Federated Learning (FL), a new type of attacks concerns the research community, namely Data Poisoning Attacks, which threaten the model integrity by maliciously altering training data. This paper introduces a…

Cryptography and Security · Computer Science 2024-04-22 Nick Galanis

Deep neural networks (DNNs) are susceptible to backdoor attacks, where adversaries poison datasets with adversary-specified triggers to implant hidden backdoors, enabling malicious manipulation of model predictions. Dataset purification…

Cryptography and Security · Computer Science 2025-06-24 Linshan Hou , Wei Luo , Zhongyun Hua , Songhua Chen , Leo Yu Zhang , Yiming Li

Recent studies have proven that deep neural networks are vulnerable to backdoor attacks. Specifically, by mixing a small number of poisoned samples into the training set, the behavior of the trained model can be maliciously controlled.…

Computer Vision and Pattern Recognition · Computer Science 2022-06-07 Pengfei Xia , Ziqiang Li , Wei Zhang , Bin Li

Federated Learning enables collaborative training of machine learning models on decentralized data. This scheme, however, is vulnerable to adversarial attacks, when some of the clients submit corrupted model updates. In real-world…

Machine Learning · Computer Science 2025-05-06 Aleksandr Karakulev , Usama Zafar , Salman Toor , Prashant Singh

This paper establishes a mathematically precise definition of dataset poisoning attack and proves that the very act of effectively poisoning a dataset ensures that the attack can be effectively detected. On top of a mathematical guarantee…

Cryptography and Security · Computer Science 2025-01-22 Jonathan Gallagher , Yasaman Esfandiari , Callen MacPhee , Michael Warren

Federated Learning (FL) represents a promising approach to typical privacy concerns associated with centralized Machine Learning (ML) deployments. Despite its well-known advantages, FL is vulnerable to security attacks such as Byzantine…

Machine Learning · Computer Science 2024-02-16 Enrique Mármol Campos , Aurora González Vidal , José Luis Hernández Ramos , Antonio Skarmeta

Due to its distributed nature, federated learning is vulnerable to poisoning attacks, in which malicious clients poison the training process via manipulating their local training data and/or local model updates sent to the cloud server,…

Cryptography and Security · Computer Science 2022-10-05 Xiaoyu Cao , Zaixi Zhang , Jinyuan Jia , Neil Zhenqiang Gong

This article presents DDP-SA, a scalable privacy-preserving federated learning framework that jointly leverages client-side local differential privacy (LDP) and full-threshold additive secret sharing (ASS) for secure aggregation. Unlike…

Cryptography and Security · Computer Science 2026-04-09 Wenjing Wei , Farid Nait-Abdesselam , Alla Jammine

Decentralized Federated Learning (DFL) remains highly vulnerable to adaptive backdoor attacks designed to bypass traditional passive defense metrics. To address this limitation, we shift the defensive paradigm toward a novel active,…

Machine Learning · Computer Science 2026-03-20 Sheng Pan , Niansheng Tang

Backdoors on federated learning will be diluted by subsequent benign updates. This is reflected in the significant reduction of attack success rate as iterations increase, ultimately failing. We use a new metric to quantify the degree of…

Cryptography and Security · Computer Science 2024-04-30 Tao Liu , Yuhang Zhang , Zhu Feng , Zhiqin Yang , Chen Xu , Dapeng Man , Wu Yang

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

Cryptography and Security · Computer Science 2021-01-21 Ximing Qiao , Yuhua Bai , Siping Hu , Ang Li , Yiran Chen , Hai Li

In federated learning (FL), although the original intention of available but not visible data is to allay data privacy concerns, it potentially brings new security threats, particularly poisoning attacks that target such not visible local…

Cryptography and Security · Computer Science 2026-03-20 Wei Sun , Bo Gao , Ke Xiong , Yuwei Wang , Pingyi Fan , Khaled Ben Letaief