English
Related papers

Related papers: Potion: Towards Poison Unlearning

200 papers

Large Language Models are typically trained on datasets collected from the web, which may inadvertently contain harmful or sensitive personal information. To address growing privacy concerns, unlearning methods have been proposed to remove…

Machine Learning · Computer Science 2025-10-23 Xiaoyu Wu , Yifei Pang , Terrance Liu , Zhiwei Steven Wu

Backdoor unlearning aims to remove backdoor-related information while preserving the model's original functionality. However, existing unlearning methods mainly focus on recovering trigger patterns but fail to restore the correct semantic…

Cryptography and Security · Computer Science 2025-07-15 Yanghao Su , Jie Zhang , Yiming Li , Tianwei Zhang , Qing Guo , Weiming Zhang , Nenghai Yu , Nils Lukas , Wenbo Zhou

We consider availability data poisoning attacks, where an adversary aims to degrade the overall test accuracy of a machine learning model by crafting small perturbations to its training data. Existing poisoning strategies can achieve the…

Cryptography and Security · Computer Science 2024-06-07 Yiyong Liu , Michael Backes , Xiao Zhang

Website Fingerprinting (WF) is an effective tool for regulating and governing the dark web. However, its performance can be significantly degraded by backdoor poisoning attacks in practical deployments. This paper aims to address the…

Cryptography and Security · Computer Science 2025-06-17 Yali Yuan , Kai Xu , Ruolin Ma , Yuchen Zhang

Data-poisoning based backdoor attacks aim to insert backdoor into models by manipulating training datasets without controlling the training process of the target model. Existing attack methods mainly focus on designing triggers or fusion…

Cryptography and Security · Computer Science 2023-07-17 Zihao Zhu , Mingda Zhang , Shaokui Wei , Li Shen , Yanbo Fan , Baoyuan Wu

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

Machine learning models trained on vast amounts of real or synthetic data often achieve outstanding predictive performance across various domains. However, this utility comes with increasing concerns about privacy, as the training data may…

Cryptography and Security · Computer Science 2024-07-09 Binhao Ma , Tianhang Zheng , Hongsheng Hu , Di Wang , Shuo Wang , Zhongjie Ba , Zhan Qin , Kui Ren

Recent studies have shown that deep learning models are very vulnerable to poisoning attacks. Many defense methods have been proposed to address this issue. However, traditional poisoning attacks are not as threatening as commonly believed.…

Machine Learning · Computer Science 2025-12-12 Yuhao He , Jinyu Tian , Xianwei Zheng , Li Dong , Yuanman Li , Jiantao Zhou

A number of online services nowadays rely upon machine learning to extract valuable information from data collected in the wild. This exposes learning algorithms to the threat of data poisoning, i.e., a coordinate attack in which a fraction…

Two widely used techniques for training supervised machine learning models on small datasets are Active Learning and Transfer Learning. The former helps to optimally use a limited budget to label new data. The latter uses large pre-trained…

Machine Learning · Computer Science 2021-01-28 Nicolas M. Müller , Konstantin Böttinger

Availability poisons exploit supervised learning (SL) algorithms by introducing class-related shortcut features in images such that models trained on poisoned data are useless for real-world datasets. Self-supervised learning (SSL), which…

Computer Vision and Pattern Recognition · Computer Science 2024-09-16 Jeremy Styborski , Mingzhi Lyu , Yi Huang , Adams Kong

Machine unlearning, the ability for a machine learning model to forget, is becoming increasingly important to comply with data privacy regulations, as well as to remove harmful, manipulated, or outdated information. The key challenge lies…

Machine Learning · Computer Science 2023-12-14 Jack Foster , Stefan Schoepf , Alexandra Brintrup

Adversaries can embed backdoors in deep learning models by introducing backdoor poison samples into training datasets. In this work, we investigate how to detect such poison samples to mitigate the threat of backdoor attacks. First, we…

Machine Learning · Computer Science 2023-06-21 Xiangyu Qi , Tinghao Xie , Jiachen T. Wang , Tong Wu , Saeed Mahloujifar , Prateek Mittal

Adversarial poisoning attacks pose huge threats to various machine learning applications. Especially, the recent accumulative poisoning attacks show that it is possible to achieve irreparable harm on models via a sequence of imperceptible…

Machine Learning · Computer Science 2023-06-07 Jianing Zhu , Xiawei Guo , Jiangchao Yao , Chao Du , Li He , Shuo Yuan , Tongliang Liu , Liang Wang , Bo Han

Federated learning is vulnerable to poisoning attacks in which malicious clients poison the global model via sending malicious model updates to the server. Existing defenses focus on preventing a small number of malicious clients from…

Cryptography and Security · Computer Science 2022-10-21 Xiaoyu Cao , Jinyuan Jia , Zaixi Zhang , Neil Zhenqiang Gong

We introduce a new class of attacks on machine learning models. We show that an adversary who can poison a training dataset can cause models trained on this dataset to leak significant private details of training points belonging to other…

Cryptography and Security · Computer Science 2022-10-07 Florian Tramèr , Reza Shokri , Ayrton San Joaquin , Hoang Le , Matthew Jagielski , Sanghyun Hong , Nicholas Carlini

With the rise of artificial intelligence and machine learning in modern computing, one of the major concerns regarding such techniques is to provide privacy and security against adversaries. We present this survey paper to cover the most…

Cryptography and Security · Computer Science 2022-02-09 Wenjun Qiu

While recent works have indicated that federated learning (FL) may be vulnerable to poisoning attacks by compromised clients, their real impact on production FL systems is not fully understood. In this work, we aim to develop a…

Machine Learning · Computer Science 2021-12-14 Virat Shejwalkar , Amir Houmansadr , Peter Kairouz , Daniel Ramage

Addressing data integrity challenges, such as unlearning the effects of data poisoning after model training, is necessary for the reliable deployment of machine learning models. State-of-the-art influence functions, such as EK-FAC and TRAK,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Wenjie Li , Jiawei Li , Pengcheng Zeng , Christian Schroeder de Witt , Ameya Prabhu , Amartya Sanyal

Machine learning systems trained on user-provided data are susceptible to data poisoning attacks, whereby malicious users inject false training data with the aim of corrupting the learned model. While recent work has proposed a number of…

Machine Learning · Computer Science 2017-11-27 Jacob Steinhardt , Pang Wei Koh , Percy Liang