English
Related papers

Related papers: How Worrying Are Privacy Attacks Against Machine L…

200 papers

Recently, recommender systems have achieved promising performances and become one of the most widely used web applications. However, recommender systems are often trained on highly sensitive user data, thus potential data leakage from…

Cryptography and Security · Computer Science 2021-09-17 Minxing Zhang , Zhaochun Ren , Zihan Wang , Pengjie Ren , Zhumin Chen , Pengfei Hu , Yang Zhang

Machine learning algorithms, when applied to sensitive data, pose a potential threat to privacy. A growing body of prior work has demonstrated that membership inference attack (MIA) can disclose specific private information in the training…

Cryptography and Security · Computer Science 2020-01-27 Bo Zhang , Ruotong Yu , Haipei Sun , Yanying Li , Jun Xu , Hui Wang

Large Language Models (LLMs) are prone to memorizing training data, which poses serious privacy risks. Two of the most prominent concerns are training data extraction and Membership Inference Attacks (MIAs). Prior research has shown that…

Machine Learning · Computer Science 2026-03-02 Ali Al Sahili , Ali Chehab , Razane Tajeddine

In the age of agentic AI, the growing deployment of multi-modal models (MMs) has introduced new attack vectors that can leak sensitive training data in MMs, causing privacy leakage. This paper investigates a black-box privacy attack, i.e.,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 David Amebley , Sayanton Dibbo

With the increasing adoption of AI, inherent security and privacy vulnerabilities formachine learning systems are being discovered. One such vulnerability makes itpossible for an adversary to obtain private information about the types of…

Machine Learning · Computer Science 2019-10-11 Samyadeep Basu , Rauf Izmailov , Chris Mesterharm

Membership Inference Attacks (MIAs) are widely used to quantify training data memorization and assess privacy risks. Standard evaluation requires repeated retraining, which is computationally costly for large models. One-run methods (single…

Machine Learning · Computer Science 2026-02-06 Mathieu Even , Clément Berenfeld , Linus Bleistein , Tudor Cebere , Julie Josse , Aurélien Bellet

We study what provable privacy attacks can be shown on trained, 2-layer ReLU neural networks. We explore two types of attacks; data reconstruction attacks, and membership inference attacks. We prove that theoretical results on the implicit…

Machine Learning · Computer Science 2025-02-11 Guy Smorodinsky , Gal Vardi , Itay Safran

With an increase in low-cost machine learning APIs, advanced machine learning models may be trained on private datasets and monetized by providing them as a service. However, privacy researchers have demonstrated that these models may leak…

Recently, it has been shown that Machine Learning models can leak sensitive information about their training data. This information leakage is exposed through membership and attribute inference attacks. Although many attack strategies have…

Machine Learning · Computer Science 2023-03-08 Ganesh Del Grosso , Georg Pichler , Catuscia Palamidessi , Pablo Piantanida

We study the question of how well machine learning (ML) models trained on a certain data set provide privacy for the training data, or equivalently, whether it is possible to reverse-engineer the training data from a given ML model. While…

Machine Learning · Computer Science 2022-04-20 Stefan Rass , Sandra König , Jasmin Wachter , Manuel Egger , Manuel Hobisch

Most current approaches for protecting privacy in machine learning (ML) assume that models exist in a vacuum. Yet, in reality, these models are part of larger systems that include components for training data filtering, output monitoring,…

The use of personal data for training machine learning systems comes with a privacy threat and measuring the level of privacy of a model is one of the major challenges in machine learning today. Identifying training data based on a trained…

Machine Learning · Computer Science 2022-03-24 Ganesh Del Grosso , Hamid Jalalzai , Georg Pichler , Catuscia Palamidessi , Pablo Piantanida

Recent research shows that large language models are susceptible to privacy attacks that infer aspects of the training data. However, it is unclear if simpler generative models, like topic models, share similar vulnerabilities. In this…

Cryptography and Security · Computer Science 2024-09-24 Nico Manzonelli , Wanrong Zhang , Salil Vadhan

The increasing deployment of Machine Learning (ML) models in sensitive domains motivates the need for robust, practical privacy assessment tools. PrivacyGuard is a comprehensive tool for empirical differential privacy (DP) analysis,…

Machine Learning · Computer Science 2025-10-28 Luca Melis , Matthew Grange , Iden Kalemaj , Karan Chadha , Shengyuan Hu , Elena Kashtelyan , Will Bullock

Federated Learning (FL) offers a promising framework for collaboratively training machine learning models across decentralized genomic datasets without direct data sharing. While this approach preserves data locality, it remains susceptible…

Cryptography and Security · Computer Science 2025-05-13 Chetan Pathade , Shubham Patil

Machine learning is data hungry; the more data a model has access to in training, the more likely it is to perform well at inference time. Distinct parties may want to combine their local data to gain the benefits of a model trained on a…

Cryptography and Security · Computer Science 2019-01-09 Jamie Hayes , Olga Ohrimenko

In this paper we develop state-of-the-art privacy attacks against Large Language Models (LLMs), where an adversary with some access to the model tries to learn something about the underlying training data. Our headline results are new…

Cryptography and Security · Computer Science 2024-07-16 Jeffrey G. Wang , Jason Wang , Marvin Li , Seth Neel

Commercial companies that collect user data on a large scale have been the main beneficiaries of this trend since the success of deep learning techniques is directly proportional to the amount of data available for training. Massive data…

Cryptography and Security · Computer Science 2020-06-30 Saichethan Miriyala Reddy , Saisree Miriyala

Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications. In this paper, we study the privacy implications of fine-tuning LLMs on user data. To this end, we consider a…

Cryptography and Security · Computer Science 2024-02-27 Nikhil Kandpal , Krishna Pillutla , Alina Oprea , Peter Kairouz , Christopher A. Choquette-Choo , Zheng Xu

Membership inference attacks (MIAs) have been extensively studied in large language models (LLMs) and vision-language models (VLMs), yet their implications for vision-language-action (VLA) models remain largely unexplored. VLA models differ…

Cryptography and Security · Computer Science 2026-05-11 Yuefeng Peng , Mingzhe Li , Kejing Xia , Renhao Zhang , Amir Houmansadr