English
Related papers

Related papers: Trade-offs and Guarantees of Adversarial Represent…

200 papers

Adversarial training is among the most effective techniques to improve the robustness of models against adversarial perturbations. However, the full effect of this approach on models is not well understood. For example, while adversarial…

Machine Learning · Computer Science 2021-01-19 Mohammad Mehrabi , Adel Javanmard , Ryan A. Rossi , Anup Rao , Tung Mai

In this paper we consider the setting where machine learning models are retrained on updated datasets in order to incorporate the most up-to-date information or reflect distribution shifts. We investigate whether one can infer information…

Machine Learning · Computer Science 2024-01-04 Tian Hui , Farhad Farokhi , Olga Ohrimenko

We consider the problem of maintaining sparsity in private distributed storage of confidential machine learning data. In many applications, e.g., face recognition, the data used in machine learning algorithms is represented by sparse…

Information Theory · Computer Science 2022-06-15 Marvin Xhemrishi , Maximilian Egger , Rawad Bitar

Learning transferable data representations from abundant unlabeled data remains a central challenge in machine learning. Although numerous self-supervised learning methods have been proposed to address this challenge, a significant class of…

Machine Learning · Statistics 2025-10-21 Chenguang Duan , Yuling Jiao , Huazhen Lin , Wensen Ma , Jerry Zhijian Yang

Adversarial representation learning aims to learn data representations for a target task while removing unwanted sensitive information at the same time. Existing methods learn model parameters iteratively through stochastic gradient…

Machine Learning · Computer Science 2021-09-14 Bashir Sadeghi , Lan Wang , Vishnu Naresh Boddeti

By locally encoding raw data into intermediate features, collaborative inference enables end users to leverage powerful deep learning models without exposure of sensitive raw data to cloud servers. However, recent studies have revealed that…

Machine Learning · Computer Science 2025-04-04 Song Xia , Yi Yu , Wenhan Yang , Meiwen Ding , Zhuo Chen , Ling-Yu Duan , Alex C. Kot , Xudong Jiang

Ensuring the usefulness of electronic data sources while providing necessary privacy guarantees is an important unsolved problem. This problem drives the need for an analytical framework that can quantify the safety of personally…

Information Theory · Computer Science 2016-11-18 Lalitha Sankar , S. Raj Rajagopalan , H. Vincent Poor

Machine learning is being integrated into a growing number of critical systems with far-reaching impacts on society. Unexpected behaviour and unfair decision processes are coming under increasing scrutiny due to this widespread use and its…

Machine Learning · Computer Science 2020-09-02 Pieter Delobelle , Paul Temple , Gilles Perrouin , Benoît Frénay , Patrick Heymans , Bettina Berendt

We provide a general framework for characterizing the trade-off between accuracy and robustness in supervised learning. We propose a method and define quantities to characterize the trade-off between accuracy and robustness for a given…

Machine Learning · Computer Science 2025-05-26 Zhun Deng , Cynthia Dwork , Jialiang Wang , Yao Zhao

This paper introduces a modeling framework for distributed regression with agents/experts observing attribute-distributed data (heterogeneous data). Under this model, a new algorithm, the iterative covariance optimization algorithm (ICOA),…

Distributed, Parallel, and Cluster Computing · Computer Science 2009-07-30 Haipeng Zheng , Sanjeev R. Kulkarni , H. Vincent Poor

Information leakage is becoming a critical problem as various information becomes publicly available by mistake, and machine learning models train on that data to provide services. As a result, one's private information could easily be…

Machine Learning · Computer Science 2022-12-02 Geon Heo , Steven Euijong Whang

Trustworthy Federated Learning (TFL) typically leverages protection mechanisms to guarantee privacy. However, protection mechanisms inevitably introduce utility loss or efficiency reduction while protecting data privacy. Therefore,…

Machine Learning · Computer Science 2024-02-29 Xiaojin Zhang , Yan Kang , Lixin Fan , Kai Chen , Qiang Yang

We study statistical risk minimization problems under a privacy model in which the data is kept confidential even from the learner. In this local privacy framework, we establish sharp upper and lower bounds on the convergence rates of…

Machine Learning · Statistics 2013-10-11 John C. Duchi , Michael I. Jordan , Martin J. Wainwright

Data for deep learning should be protected for privacy preserving. Researchers have come up with the notion of learnable image encryption to satisfy the requirement. However, existing privacy preserving approaches have never considered the…

Image and Video Processing · Electrical Eng. & Systems 2019-08-01 MaungMaung AprilPyone , Warit Sirichotedumrong , Hitoshi Kiya

We consider membership inference attacks, one of the main privacy issues in machine learning. These recently developed attacks have been proven successful in determining, with confidence better than a random guess, whether a given sample…

Machine Learning · Computer Science 2019-11-20 Rauf Izmailov , Peter Lin , Chris Mesterharm , Samyadeep Basu

The arms race between attacks and defenses for machine learning models has come to a forefront in recent years, in both the security community and the privacy community. However, one big limitation of previous research is that the security…

Machine Learning · Statistics 2019-08-27 Liwei Song , Reza Shokri , Prateek Mittal

Federated learning (FL) enables participating parties to collaboratively build a global model with boosted utility without disclosing private data information. Appropriate protection mechanisms have to be adopted to fulfill the opposing…

Machine Learning · Computer Science 2023-07-24 Xiaojin Zhang , Yan Kang , Kai Chen , Lixin Fan , Qiang Yang

Deep models, while being extremely versatile and accurate, are vulnerable to adversarial attacks: slight perturbations that are imperceptible to humans can completely flip the prediction of deep models. Many attack and defense mechanisms…

Machine Learning · Computer Science 2019-07-30 Kaiwen Wu , Yaoliang Yu

This paper aims to improve privacy-preserving visual recognition, an increasingly demanded feature in smart camera applications, by formulating a unique adversarial training framework. The proposed framework explicitly learns a degradation…

Computer Vision and Pattern Recognition · Computer Science 2020-10-26 Zhenyu Wu , Zhangyang Wang , Zhaowen Wang , Hailin Jin

Neural networks have demonstrated state-of-the-art performance in various machine learning fields. However, the introduction of malicious perturbations in input data, known as adversarial examples, has been shown to deceive neural network…

Machine Learning · Computer Science 2023-02-06 Dennis Y. Menn , Tzu-hsun Feng , Hung-yi Lee