English
Related papers

Related papers: Improved Certified Defenses against Data Poisoning…

200 papers

The goal of federated learning (FL) is to train one global model by aggregating model parameters updated independently on edge devices without accessing users' private data. However, FL is susceptible to backdoor attacks where a small…

Cryptography and Security · Computer Science 2022-02-24 Yein Kim , Huili Chen , Farinaz Koushanfar

Voice authentication systems remain susceptible to two major threats: backdoor triggered attacks and targeted data poisoning attacks. This dual vulnerability is critical because conventional solutions typically address each threat type…

Cryptography and Security · Computer Science 2025-05-07 Alireza Mohammadi , Keshav Sood , Dhananjay Thiruvady , Asef Nazari

Federated learning (FL) enables learning a global machine learning model from local data distributed among a set of participating workers. This makes it possible i) to train more accurate models due to learning from rich joint training…

Machine Learning · Computer Science 2025-11-25 Najeeb Jebreel , Josep Domingo-Ferrer

Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoning attacks have…

Machine Learning · Computer Science 2019-09-26 Luis Muñoz-González , Bjarne Pfitzner , Matteo Russo , Javier Carnerero-Cano , Emil C. Lupu

Federated learning is a promising direction to tackle the privacy issues related to sharing patients' sensitive data. Often, federated systems in the medical image analysis domain assume that the participating local clients are…

Machine Learning · Computer Science 2023-08-16 Indu Joshi , Priyank Upadhya , Gaurav Kumar Nayak , Peter Schüffler , Nassir Navab

The unprecedented availability of training data fueled the rapid development of powerful neural networks in recent years. However, the need for such large amounts of data leads to potential threats such as poisoning attacks: adversarial…

Machine Learning · Computer Science 2024-03-21 Fabio De Gaspari , Dorjan Hitaj , Luigi V. Mancini

Targeted clean-label data poisoning is a type of adversarial attack on machine learning systems in which an adversary injects a few correctly-labeled, minimally-perturbed samples into the training data, causing a model to misclassify a…

Machine Learning · Computer Science 2020-08-14 Neehar Peri , Neal Gupta , W. Ronny Huang , Liam Fowl , Chen Zhu , Soheil Feizi , Tom Goldstein , John P. Dickerson

Diffusion-based purification defenses leverage diffusion models to remove crafted perturbations of adversarial examples and achieve state-of-the-art robustness. Recent studies show that even advanced attacks cannot break such defenses…

Cryptography and Security · Computer Science 2024-01-05 Mintong Kang , Dawn Song , Bo Li

AI-enabled critical infrastructures (ACIs) integrate artificial intelligence (AI) technologies into various essential systems and services that are vital to the functioning of society, offering significant implications for efficiency,…

Cryptography and Security · Computer Science 2024-05-27 Zehang Deng , Ruoxi Sun , Minhui Xue , Sheng Wen , Seyit Camtepe , Surya Nepal , Yang Xiang

Deep Neural Networks (DNNs) are susceptible to backdoor attacks, where adversaries poison training data to implant backdoor into the victim model. Current backdoor defenses on poisoned data often suffer from high computational costs or low…

Multimedia · Computer Science 2025-07-28 Binyan Xu , Fan Yang , Xilin Dai , Di Tang , Kehuan Zhang

Federated Averaging remains the most widely used aggregation strategy in federated learning due to its simplicity and scalability. However, its performance degrades significantly in non-IID data settings, where client distributions are…

Machine Learning · Computer Science 2025-03-07 Marco Arazzi , Mert Cihangiroglu , Antonino Nocera

Backdoor attack has been considered as a serious security threat to deep neural networks (DNNs). Poisoned sample detection (PSD) that aims at filtering out poisoned samples from an untrustworthy training dataset has shown very promising…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Mingda Zhang , Mingli Zhu , Zihao Zhu , Baoyuan Wu

Federated learning is a distributed framework designed to address privacy concerns. However, it introduces new attack surfaces, which are especially prone when data is non-Independently and Identically Distributed. Existing approaches fail…

Cryptography and Security · Computer Science 2025-05-27 Hyejun Jeong , Hamin Son , Seohu Lee , Jayun Hyun , Tai-Myoung Chung

Federated learning (FL) aims to perform privacy-preserving machine learning on distributed data held by multiple data owners. To this end, FL requires the data owners to perform training locally and share the gradient updates (instead of…

Machine Learning · Computer Science 2022-09-14 Sanjay Kariyappa , Chuan Guo , Kiwan Maeng , Wenjie Xiong , G. Edward Suh , Moinuddin K Qureshi , Hsien-Hsin S. Lee

Federated learning (FL) is an emerging paradigm that allows a central server to train machine learning models using remote users' data. Despite its growing popularity, FL faces challenges in preserving the privacy of local datasets, its…

Cryptography and Security · Computer Science 2025-05-09 Natalie Lang , Nir Shlezinger , Rafael G. L. D'Oliveira , Salim El Rouayheb

As one kind of distributed machine learning technique, federated learning enables multiple clients to build a model across decentralized data collaboratively without explicitly aggregating the data. Due to its ability to break data silos,…

Cryptography and Security · Computer Science 2023-06-07 Junchuan Lianga , Rong Wang , Chaosheng Feng , Chin-Chen Chang

Federated Learning (FL) is a distributed training paradigm wherein participants collaborate to build a global model while ensuring the privacy of the involved data, which remains stored on participant devices. However, proposals aiming to…

Machine Learning · Computer Science 2025-11-05 Nicolas Riccieri Gardin Assumpcao , Leandro Villas

Adversarial patch attacks that craft the pixels in a confined region of the input images show their powerful attack effectiveness in physical environments even with noises or deformations. Existing certified defenses towards adversarial…

Computer Vision and Pattern Recognition · Computer Science 2021-11-05 Husheng Han , Kaidi Xu , Xing Hu , Xiaobing Chen , Ling Liang , Zidong Du , Qi Guo , Yanzhi Wang , Yunji Chen

In this thesis, a completely revisited data protection scheme based on selective encryption is presented. First, this new scheme is agnostic in term of data format, second it has a parallel architecture using GPGPU allowing performance to…

Cryptography and Security · Computer Science 2018-03-14 Han Qiu

While neural networks have achieved high accuracy on standard image classification benchmarks, their accuracy drops to nearly zero in the presence of small adversarial perturbations to test inputs. Defenses based on regularization and…

Machine Learning · Computer Science 2020-11-03 Aditi Raghunathan , Jacob Steinhardt , Percy Liang