English
Related papers

Related papers: Quantifying the Privacy Risks of Learning High-Dim…

200 papers

Model explanations provide transparency into a trained machine learning model's blackbox behavior to a model builder. They indicate the influence of different input attributes to its corresponding model prediction. The dependency of…

Cryptography and Security · Computer Science 2022-09-09 Vasisht Duddu , Antoine Boutet

Though many deep learning-based models have made great progress in vulnerability detection, we have no good understanding of these models, which limits the further advancement of model capability, understanding of the mechanism of model…

Software Engineering · Computer Science 2024-08-15 Chao Ni , Liyu Shen , Xiaodan Xu , Xin Yin , Shaohua Wang

Fine-tuning large language models on private data for downstream applications poses significant privacy risks in potentially exposing sensitive information. Several popular community platforms now offer convenient distribution of a large…

Machine Learning · Computer Science 2024-09-02 Md Rafi Ur Rashid , Jing Liu , Toshiaki Koike-Akino , Shagufta Mehnaz , Ye Wang

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

With the rapid expansion of data lakes storing health data and hosting AI algorithms, a prominent concern arises: how safe is it to export machine learning models from these data lakes? In particular, deep network models, widely used for…

Cryptography and Security · Computer Science 2025-12-09 Huiyu Li , Nicholas Ayache , Hervé Delingette

Deep learning model developers often use cloud GPU resources to experiment with large data and models that need expensive setups. However, this practice raises privacy concerns. Adversaries may be interested in: 1) personally identifiable…

Machine Learning · Computer Science 2019-04-22 Sagar Sharma , Keke Chen

Deep neural networks are known to have security issues. One particular threat is the Trojan attack. It occurs when the attackers stealthily manipulate the model's behavior through Trojaned training samples, which can later be exploited.…

Machine Learning · Computer Science 2021-06-14 Songzhu Zheng , Yikai Zhang , Hubert Wagner , Mayank Goswami , Chao Chen

Federated learning (FL) has become a key component in various language modeling applications such as machine translation, next-word prediction, and medical record analysis. These applications are trained on datasets from many FL…

Cryptography and Security · Computer Science 2025-12-11 Md Rafi Ur Rashid , Vishnu Asutosh Dasu , Kang Gu , Najrin Sultana , Shagufta Mehnaz

In machine learning, curation is used to select the most valuable data for improving both model accuracy and computational efficiency. Recently, curation has also been explored as a solution for private machine learning: rather than…

Machine Learning · Computer Science 2026-03-03 Dariush Wahdany , Matthew Jagielski , Adam Dziedzic , Franziska Boenisch

Differential privacy (DP) is a popular mechanism for training machine learning models with bounded leakage about the presence of specific points in the training data. The cost of differential privacy is a reduction in the model's accuracy.…

Machine Learning · Computer Science 2019-10-29 Eugene Bagdasaryan , Vitaly Shmatikov

While diffusion models have recently demonstrated remarkable progress in generating realistic images, privacy risks also arise: published models or APIs could generate training images and thus leak privacy-sensitive training information. In…

Machine Learning · Computer Science 2024-04-23 Zhangheng Li , Junyuan Hong , Bo Li , Zhangyang Wang

In a model extraction attack, an adversary steals a copy of a remotely deployed machine learning model, given oracle prediction access. We taxonomize model extraction attacks around two objectives: *accuracy*, i.e., performing well on the…

Machine Learning · Computer Science 2020-03-05 Matthew Jagielski , Nicholas Carlini , David Berthelot , Alex Kurakin , Nicolas Papernot

Understanding when and how much a model gradient leaks information about the training sample is an important question in privacy. In this paper, we present a surprising result: even without training or memorizing the data, we can fully…

Machine Learning · Computer Science 2023-06-13 Zihan Wang , Jason D. Lee , Qi Lei

Differential privacy is a strong notion for privacy that can be used to prove formal guarantees, in terms of a privacy budget, $\epsilon$, about how much information is leaked by a mechanism. However, implementations of privacy-preserving…

Machine Learning · Computer Science 2019-08-14 Bargav Jayaraman , David Evans

Membership Inference Attacks (MIAs) have emerged as a valuable framework for evaluating privacy leakage by machine learning models. Score-based MIAs are distinguished, in particular, by their ability to exploit the confidence scores that…

Machine Learning · Computer Science 2025-02-28 Gauri Pradhan , Joonas Jälkö , Marlon Tobaben , Antti Honkela

Given access to a machine learning model, can an adversary reconstruct the model's training data? This work studies this question from the lens of a powerful informed adversary who knows all the training data points except one. By…

Cryptography and Security · Computer Science 2022-04-26 Borja Balle , Giovanni Cherubin , Jamie Hayes

Meta-learning involves multiple learners, each dedicated to specific tasks, collaborating in a data-constrained setting. In current meta-learning methods, task learners locally learn models from sensitive data, termed support sets. These…

Machine Learning · Computer Science 2024-06-05 Mina Rafiei , Mohammadmahdi Maheri , Hamid R. Rabiee

In recent years, diffusion models have achieved tremendous success in the field of image generation, becoming the stateof-the-art technology for AI-based image processing applications. Despite the numerous benefits brought by recent…

Machine Learning · Computer Science 2023-08-08 Derui Zhu , Dingfan Chen , Jens Grossklags , Mario Fritz

Due to insufficient training data and the high computational cost to train a deep neural network from scratch, transfer learning has been extensively used in many deep-neural-network-based applications. A commonly used transfer learning…

Machine Learning · Computer Science 2020-01-30 Shahbaz Rezaei , Xin Liu

Maximal leakage quantifies the leakage of information from data $X \in \mathcal{X}$ due to an observation $Y$. While fundamental properties of maximal leakage, such as data processing, sub-additivity, and its connection to mutual…

Information Theory · Computer Science 2025-12-24 Anuran Makur , Japneet Singh