English
Related papers

Related papers: MemGuard: Defending against Black-Box Membership I…

200 papers

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 used to test practical privacy of machine learning models. MIAs complement formal guarantees from differential privacy (DP) under a more realistic adversary model. We analyse MIA vulnerability of…

Cryptography and Security · Computer Science 2026-02-03 Marlon Tobaben , Hibiki Ito , Joonas Jälkö , Yuan He , Antti Honkela

Named entity recognition models (NER), are widely used for identifying named entities (e.g., individuals, locations, and other information) in text documents. Machine learning based NER models are increasingly being applied in…

Cryptography and Security · Computer Science 2022-11-07 Rana Salal Ali , Benjamin Zi Hao Zhao , Hassan Jameel Asghar , Tham Nguyen , Ian David Wood , Dali Kaafar

Large language models (LLMs) show strong performance across many applications, but their ability to memorize and potentially reveal training data raises serious privacy concerns. We introduce the PopQuiz Attack, a black-box membership…

Cryptography and Security · Computer Science 2026-05-08 Zeyuan Chen , Yihan Ma , Xinyue Shen , Michael Backes , Yang Zhang

Previous studies have developed fairness methods for biased models that exhibit discriminatory behaviors towards specific subgroups. While these models have shown promise in achieving fair predictions, recent research has identified their…

Machine Learning · Computer Science 2024-08-28 Huan Tian , Guangsheng Zhang , Bo Liu , Tianqing Zhu , Ming Ding , Wanlei Zhou

It is commonplace to produce application-specific models by fine-tuning large pre-trained models using a small bespoke dataset. The widespread availability of foundation model checkpoints on the web poses considerable risks, including the…

Cryptography and Security · Computer Science 2024-04-02 Yuxin Wen , Leo Marchyok , Sanghyun Hong , Jonas Geiping , Tom Goldstein , Nicholas Carlini

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples which contain human-imperceptible perturbations. A series of defending methods, either proactive defence or reactive defence, have been proposed in the recent…

Machine Learning · Computer Science 2020-07-27 Derek Wang , Chaoran Li , Sheng Wen , Surya Nepal , Yang Xiang

Although federated learning improves privacy of training data by exchanging local gradients or parameters rather than raw data, the adversary still can leverage local gradients and parameters to obtain local training data by launching…

Machine Learning · Computer Science 2021-08-17 Xue Yang , Yan Feng , Weijun Fang , Jun Shao , Xiaohu Tang , Shu-Tao Xia , Rongxing Lu

Text-to-image generation models have recently attracted unprecedented attention as they unlatch imaginative applications in all areas of life. However, developing such models requires huge amounts of data that might contain…

Cryptography and Security · Computer Science 2022-10-04 Yixin Wu , Ning Yu , Zheng Li , Michael Backes , Yang Zhang

The vulnerability of machine learning models to membership inference attacks has received much attention in recent years. However, existing attacks mostly remain impractical due to having high false positive rates, where non-member samples…

Cryptography and Security · Computer Science 2022-04-12 Lauren Watson , Chuan Guo , Graham Cormode , Alex Sablayrolles

Membership inference attacks allow a malicious entity to predict whether a sample is used during training of a victim model or not. State-of-the-art membership inference attacks have shown to achieve good accuracy which poses a great…

Machine Learning · Computer Science 2022-03-07 Shahbaz Rezaei , Xin Liu

The state-of-the-art for membership inference attacks on machine learning models is a class of attacks based on shadow models that mimic the behavior of the target model on subsets of held-out nonmember data. However, we find that this…

Machine Learning · Computer Science 2025-10-28 Pratiksha Thaker , Neil Kale , Zhiwei Steven Wu , Virginia Smith

Black-box adversarial attacks have demonstrated strong potential to compromise machine learning models by iteratively querying the target model or leveraging transferability from a local surrogate model. Recently, such attacks can be…

Machine Learning · Computer Science 2024-09-09 Hanbin Hong , Xinyu Zhang , Binghui Wang , Zhongjie Ba , Yuan Hong

Membership inference attacks (MIAs), which determine whether a specific data point was included in the training set of a target model, have posed severe threats in federated learning (FL). Unfortunately, existing MIA defenses, typically…

Cryptography and Security · Computer Science 2026-01-13 Li Bai , Junxu Liu , Sen Zhang , Xinwei Zhang , Qingqing Ye , Haibo Hu

Transfer learning is a useful machine learning framework that allows one to build task-specific models (student models) without significantly incurring training costs using a single powerful model (teacher model) pre-trained with a large…

Machine Learning · Computer Science 2020-10-28 Seng Pei Liew , Tsubasa Takahashi

Machine learning has seen tremendous advances in the past few years, which has lead to deep learning models being deployed in varied applications of day-to-day life. Attacks on such models using perturbations, particularly in real-life…

Machine Learning · Computer Science 2020-02-10 Siddhant Bhambri , Sumanyu Muku , Avinash Tulasi , Arun Balaji Buduru

In this paper, we study the problem of how to defend classifiers against adversarial attacks that fool the classifiers using subtly modified input data. In contrast to previous works, here we focus on the white-box adversarial defense where…

Machine Learning · Computer Science 2019-09-16 Zudi Lin , Hanspeter Pfister , Ziming Zhang

Recently, researchers have discovered that the state-of-the-art object classifiers can be fooled easily by small perturbations in the input unnoticeable to human eyes. It is also known that an attacker can generate strong adversarial…

Machine Learning · Computer Science 2018-06-28 Jihun Hamm , Akshay Mehra

Within the realm of privacy-preserving machine learning, empirical privacy defenses have been proposed as a solution to achieve satisfactory levels of training data privacy without a significant drop in model utility. Most existing defenses…

Cryptography and Security · Computer Science 2023-10-19 Caelin G. Kaplan , Chuan Xu , Othmane Marfoq , Giovanni Neglia , Anderson Santana de Oliveira

Large language models (LLMs) have become the backbone of modern natural language processing but pose privacy concerns about leaking sensitive training data. Membership inference attacks (MIAs), which aim to infer whether a sample is…

Machine Learning · Computer Science 2025-06-03 Toan Tran , Ruixuan Liu , Li Xiong