English
Related papers

Related papers: Neural Breadcrumbs: Membership Inference Attacks o…

200 papers

Model explanations improve the transparency of black-box machine learning (ML) models and their decisions; however, they can also be exploited to carry out privacy threats such as membership inference attacks (MIA). Existing works have only…

Artificial Intelligence · Computer Science 2024-04-11 Kavita Kumari , Murtuza Jadliwala , Sumit Kumar Jha , Anindya Maiti

Machine learning models are susceptible to membership inference attacks (MIAs), which aim to infer whether a sample is in the training set. Existing work utilizes gradient ascent to enlarge the loss variance of training data, alleviating…

Machine Learning · Computer Science 2024-06-19 Zhenlong Liu , Lei Feng , Huiping Zhuang , Xiaofeng Cao , Hongxin Wei

Membership Inference Attacks (MIAs) pose a critical privacy threat by enabling adversaries to determine whether a specific sample was included in a model's training dataset. Despite extensive research on MIAs, systematic comparisons between…

Cryptography and Security · Computer Science 2025-10-21 Owais Makroo , Siva Rajesh Kasa , Sumegh Roychowdhury , Karan Gupta , Nikhil Pattisapu , Santhosh Kasa , Sumit Negi

Large vision-language models (LVLMs) have demonstrated outstanding performance in many downstream tasks. However, LVLMs are trained on large-scale datasets, which can pose privacy risks if training images contain sensitive information.…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Zongyu Wu , Minhua Lin , Zhiwei Zhang , Fali Wang , Xianren Zhang , Xiang Zhang , Suhang Wang

The memorization of training data in large language models (LLMs) poses significant privacy and copyright concerns. Existing data extraction methods, particularly heuristic-based divergence attacks, often exhibit limited success and offer…

Computation and Language · Computer Science 2025-11-11 Myeongseob Ko , Nikhil Reddy Billa , Adam Nguyen , Charles Fleming , Ming Jin , Ruoxi Jia

Large Language Models (LLMs) are trained on large-scale web data, which makes it difficult to grasp the contribution of each text. This poses the risk of leaking inappropriate data such as benchmarks, personal information, and copyrighted…

Computation and Language · Computer Science 2024-04-18 Masahiro Kaneko , Youmi Ma , Yuki Wata , Naoaki Okazaki

In several jurisdictions, the regulatory framework on the release and sharing of personal data is being extended to machine learning (ML). The implicit assumption is that disclosing a trained ML model entails a privacy risk for any personal…

Cryptography and Security · Computer Science 2025-11-14 Josep Domingo-Ferrer

In the text processing context, most ML models are built on word embeddings. These embeddings are themselves trained on some datasets, potentially containing sensitive data. In some cases this training is done independently, in other cases,…

Computation and Language · Computer Science 2021-06-23 Saeed Mahloujifar , Huseyin A. Inan , Melissa Chase , Esha Ghosh , Marcello Hasegawa

The data used to train deep neural network (DNN) models in applications such as healthcare and finance typically contain sensitive information. A DNN model may suffer from overfitting. Overfitted models have been shown to be susceptible to…

Machine Learning · Computer Science 2022-12-19 Arezoo Rajabi , Dinuka Sahabandu , Luyao Niu , Bhaskar Ramasubramanian , Radha Poovendran

Large Language Models (LLMs) have recently demonstrated remarkable performance in generating high-quality tabular synthetic data. In practice, two primary approaches have emerged for adapting LLMs to tabular data generation: (i) fine-tuning…

Machine Learning · Computer Science 2026-05-12 Joshua Ward , Bochao Gu , Chi-Hua Wang , Guang Cheng

Adapting Large Language Models (LLMs) to specific tasks introduces concerns about computational efficiency, prompting an exploration of efficient methods such as In-Context Learning (ICL). However, the vulnerability of ICL to privacy…

Cryptography and Security · Computer Science 2024-09-04 Rui Wen , Zheng Li , Michael Backes , Yang Zhang

Federated Large Language Models (FedLLMs) enable multiple parties to collaboratively fine-tune LLMs without sharing raw data, addressing challenges of limited resources and privacy concerns. Despite data localization, shared gradients can…

Machine Learning · Computer Science 2026-04-24 Guilin Deng , Silong Chen , Yuchuan Luo , Yi Liu , Songlei Wang , Zhiping Cai , Lin Liu , Xiaohua Jia , Shaojing Fu

Machine learning (ML) has become a core component of many real-world applications and training data is a key factor that drives current progress. This huge success has led Internet companies to deploy machine learning as a service (MLaaS).…

Cryptography and Security · Computer Science 2018-12-18 Ahmed Salem , Yang Zhang , Mathias Humbert , Pascal Berrang , Mario Fritz , Michael Backes

Membership inference attacks (MIAs) test whether a data point was part of a model's training set, posing serious privacy risks. Existing methods often depend on shadow models or heavy query access, which limits their practicality. We…

Machine Learning · Computer Science 2025-10-28 Yongchao Huang , Pengfei Zhang , Shahzad Mumtaz

Membership Inference Attacks (MIAs) serve as a fundamental auditing tool for evaluating training data leakage in machine learning models. However, existing methodologies predominantly rely on static, handcrafted heuristics that lack…

Cryptography and Security · Computer Science 2026-04-02 Ruhao Liu , Weiqi Huang , Qi Li , Xinchao Wang

Generative AI systems are quickly improving, now able to produce believable output in several modalities including images, text, and audio. However, this fast development has prompted increased scrutiny concerning user privacy and the use…

Cryptography and Security · Computer Science 2025-12-29 Kurtis Chow , Omar Samiullah , Vinesh Sridhar , Hewen Zhang

Membership inference attacks (MIAs) are popular methods for empirically assessing the leakage of sensitive information in the training data through models or statistics learned from the data. The MIA vulnerability is often evaluated through…

Machine Learning · Computer Science 2026-05-26 Joonas Jälkö , Gauri Pradhan , Ossi Räisä , Antti Honkela

This report summarizes all the MIA experiments (Membership Inference Attacks) of the Embedding Attack Project, including threat models, experimental setup, experimental results, findings and discussion. Current results cover the evaluation…

Machine Learning · Computer Science 2024-01-26 Jiameng Pu , Zafar Takhirov

The widespread collection and sharing of location data, even in aggregated form, raises major privacy concerns. Previous studies used meta-classifier-based membership inference attacks~(MIAs) with multi-layer perceptrons~(MLPs) to estimate…

Cryptography and Security · Computer Science 2024-12-31 Yuhan Liu , Florent Guepin , Igor Shilov , Yves-Alexandre De Montjoye

Artificial intelligence systems are prevalent in everyday life, with use cases in retail, manufacturing, health, and many other fields. With the rise in AI adoption, associated risks have been identified, including privacy risks to the…

Machine Learning · Computer Science 2024-07-19 Shlomit Shachor , Natalia Razinkov , Abigail Goldsteen