English
Related papers

Related papers: UTrace: Poisoning Forensics for Private Collaborat…

200 papers

Data poisoning attacks aim to manipulate the model produced by a learning algorithm by adversarially modifying the training set. We consider differential privacy as a defensive measure against this type of attack. We show that such learners…

Machine Learning · Computer Science 2019-07-08 Yuzhe Ma , Xiaojin Zhu , Justin Hsu

Current unlearning methods for LLMs optimize on the private information they seek to remove by incorporating it into their fine-tuning data. We argue this not only risks reinforcing exposure to sensitive data, but also fundamentally…

Machine Learning · Computer Science 2026-03-03 Yan Scholten , Sophie Xhonneux , Leo Schwinn , Stephan Günnemann

With the increasing adoption of data-hungry machine learning algorithms, personal data privacy has emerged as one of the key concerns that could hinder the success of digital transformation. As such, Privacy-Preserving Machine Learning…

Cryptography and Security · Computer Science 2022-04-22 Ziyao Liu , Jiale Guo , Kwok-Yan Lam , Jun Zhao

Federated learning (FL) enables collaborative model training while preserving data privacy, but its decentralized nature exposes it to client-side data poisoning attacks (DPAs) and model poisoning attacks (MPAs) that degrade global model…

Cryptography and Security · Computer Science 2025-02-07 Heyi Zhang , Yule Liu , Xinlei He , Jun Wu , Tianshuo Cong , Xinyi Huang

Poisoning attacks, in which an attacker adversarially manipulates the training dataset of a machine learning (ML) model, pose a significant threat to ML security. Beta Poisoning is a recently proposed poisoning attack that disrupts model…

Cryptography and Security · Computer Science 2025-08-05 Nilufer Gulciftci , M. Emre Gursoy

As machine learning becomes a practice and commodity, numerous cloud-based services and frameworks are provided to help customers develop and deploy machine learning applications. While it is prevalent to outsource model training and…

Cryptography and Security · Computer Science 2018-07-16 Tianwei Zhang , Zecheng He , Ruby B. Lee

Membership inference attacks seek to infer the membership of individual training instances of a privately trained model. This paper presents a membership privacy analysis and evaluation system, called MPLens, with three unique…

Cryptography and Security · Computer Science 2019-11-25 Stacey Truex , Ling Liu , Mehmet Emre Gursoy , Wenqi Wei , Lei Yu

Though vertical federated learning (VFL) is generally considered to be privacy-preserving, recent studies have shown that VFL system is vulnerable to label inference attacks originating from various attack surfaces. Among these attacks, the…

Cryptography and Security · Computer Science 2026-01-23 Juntao Tan , Lan Zhang , Zhonghao Hu , Kai Yang , Peng Ran , Bo Li

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

Recent studies have shown that Large Language Models (LLMs) are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a…

Computation and Language · Computer Science 2025-10-10 Sanhanat Sivapiromrat , Caiqi Zhang , Marco Basaldella , Nigel Collier

We often interact with untrusted parties. Prioritization of privacy can limit the effectiveness of these interactions, as achieving certain goals necessitates sharing private data. Traditionally, addressing this challenge has involved…

Cryptography and Security · Computer Science 2025-01-16 Ilia Shumailov , Daniel Ramage , Sarah Meiklejohn , Peter Kairouz , Florian Hartmann , Borja Balle , Eugene Bagdasarian

Multimodal contrastive learning uses various data modalities to create high-quality features, but its reliance on extensive data sources on the Internet makes it vulnerable to backdoor attacks. These attacks insert malicious behaviors…

Cryptography and Security · Computer Science 2024-10-01 Kuanrong Liu , Siyuan Liang , Jiawei Liang , Pengwen Dai , Xiaochun Cao

Recent research has successfully demonstrated new types of data poisoning attacks. To address this problem, some researchers have proposed both offline and online data poisoning detection defenses which employ machine learning algorithms to…

Cryptography and Security · Computer Science 2021-05-24 Jack W. Stokes , Paul England , Kevin Kane

Machine Unlearning (MU) aims to remove target training data from a trained model so that the removed data no longer influences the model's behavior, fulfilling "right to be forgotten" obligations under data privacy laws. Yet, we observe…

Cryptography and Security · Computer Science 2026-01-27 Jaeung Lee , Suhyeon Yu , Yurim Jang , Simon S. Woo , Jaemin Jo

Over the years, the technological landscape has evolved, reshaping the security posture of organisations and increasing their exposure to cybersecurity threats, many originating from within. Insider threats remain a major challenge,…

Cryptography and Security · Computer Science 2025-10-24 Selma Shikonde , Mike Wa Nkongolo

We propose protected pipelines or props for short, a new approach for authenticated, privacy-preserving access to deep-web data for machine learning (ML). By permitting secure use of vast sources of deep-web data, props address the systemic…

Cryptography and Security · Computer Science 2024-10-29 Ari Juels , Farinaz Koushanfar

To address the growing demand for privacy protection in machine learning, we propose a novel and efficient machine unlearning approach for \textbf{L}arge \textbf{M}odels, called \textbf{LM}Eraser. Existing unlearning research suffers from…

Machine Learning · Computer Science 2024-04-18 Jie Xu , Zihan Wu , Cong Wang , Xiaohua Jia

Federated learning is emerging as a machine learning technique that trains a model across multiple decentralized parties. It is renowned for preserving privacy as the data never leaves the computational devices, and recent approaches…

Machine Learning · Computer Science 2021-06-25 Yuchen Li , Yifan Bao , Liyao Xiang , Junhan Liu , Cen Chen , Li Wang , Xinbing Wang

Imitation Learning has provided a promising approach to learning complex robot behaviors from expert demonstrations. However, learned policies can make errors that lead to safety violations, which limits their deployment in safety-critical…

Robotics · Computer Science 2025-08-06 Le Qiu , Yusuf Umut Ciftci , Somil Bansal

Organizations are collecting vast amounts of data, but they often lack the capabilities needed to fully extract insights. As a result, they increasingly share data with external experts, such as analysts or researchers, to gain value from…

Machine Learning · Computer Science 2025-05-16 Yusi Wei , Hande Y. Benson , Joseph K. Agor , Muge Capan