English
Related papers

Related papers: Re-thinking Model Inversion Attacks Against Deep N…

200 papers

Membership inference attacks (MIA) try to detect if data samples were used to train a neural network model, e.g. to detect copyright abuses. We show that models with higher dimensional input and output are more vulnerable to MIA, and…

Machine Learning · Computer Science 2021-08-19 Avital Shafran , Shmuel Peleg , Yedid Hoshen

Machine learning models' goal is to make correct predictions for specific tasks by learning important properties and patterns from data. By doing so, there is a chance that the model learns properties that are unrelated to its primary task.…

Cryptography and Security · Computer Science 2021-04-28 Mathias P. M. Parisot , Balazs Pejo , Dayana Spagnuelo

Reconstruction attacks and defenses are essential in understanding the data leakage problem in machine learning. However, prior work has centered around empirical observations of gradient inversion attacks, lacks theoretical grounding, and…

Cryptography and Security · Computer Science 2025-03-25 Sheng Liu , Zihan Wang , Yuxiao Chen , Qi Lei

Deep learning models have an intrinsic privacy issue as they memorize parts of their training data, creating a privacy leakage. Membership Inference Attacks (MIA) exploit it to obtain confidential information about the data used for…

Cryptography and Security · Computer Science 2025-03-13 Daniel Jiménez-López , Nuria Rodríguez-Barroso , M. Victoria Luzón , Francisco Herrera

A Model Inversion (MI) attack based on Generative Adversarial Networks (GAN) aims to recover the private training data from complex deep learning models by searching codes in the latent space. However, they merely search a deterministic…

Machine Learning · Computer Science 2024-04-23 Huan Bao , Kaimin Wei , Yongdong Wu , Jin Qian , Robert H. Deng

Despite the broad application of Machine Learning models as a Service (MLaaS), they are vulnerable to model stealing attacks. These attacks can replicate the model functionality by using the black-box query process without any prior…

Cryptography and Security · Computer Science 2023-08-04 Jun Guo , Aishan Liu , Xingyu Zheng , Siyuan Liang , Yisong Xiao , Yichao Wu , Xianglong Liu

Large language models (LLMs) have transformed natural language processing, but their ability to memorize training data poses significant privacy risks. This paper investigates model inversion attacks on the Llama 3.2 model, a multilingual…

Machine Learning · Computer Science 2025-07-08 Sathesh P. Sivashanmugam

Recent model inversion attack algorithms permit adversaries to reconstruct a neural network's private and potentially sensitive training data by repeatedly querying the network. In this work, we develop a novel network architecture that…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Sayanton V. Dibbo , Adam Breuer , Juston Moore , Michael Teti

Membership inference (MI) determines if a sample was part of a victim model training set. Recent development of MI attacks focus on record-level membership inference which limits their application in many real-world scenarios. For example,…

Machine Learning · Computer Science 2022-04-27 Guoyao Li , Shahbaz Rezaei , Xin Liu

Supervised Finetuning (SFT) has become one of the primary methods for adapting a large language model (LLM) with extensive pre-trained knowledge to domain-specific, instruction-following tasks. SFT datasets, composed of instruction-response…

Cryptography and Security · Computer Science 2026-05-13 Sae Furukawa , Alina Oprea

Increasing use of ML technologies in privacy-sensitive domains such as medical diagnoses, lifestyle predictions, and business decisions highlights the need to better understand if these ML technologies are introducing leakages of sensitive…

Cryptography and Security · Computer Science 2020-12-08 Shagufta Mehnaz , Ninghui Li , Elisa Bertino

Membership inference (MI) attacks exploit the fact that machine learning algorithms sometimes leak information about their training data through the learned model. In this work, we study membership inference in the white-box setting in…

Machine Learning · Computer Science 2020-06-26 Klas Leino , Matt Fredrikson

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

Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…

Cryptography and Security · Computer Science 2020-12-10 Liwei Song , Prateek Mittal

With the wide-spread application of machine learning models, it has become critical to study the potential data leakage of models trained on sensitive data. Recently, various membership inference (MI) attacks are proposed to determine if a…

Cryptography and Security · Computer Science 2023-05-01 Shahbaz Rezaei , Xin Liu

The pervasive deployment of deep learning models across critical domains has concurrently intensified privacy concerns due to their inherent propensity for data memorization. While Membership Inference Attacks (MIAs) serve as the gold…

Machine Learning · Computer Science 2026-04-16 Chihan Huang , Huaijin Wang , Shuai Wang

Foundation models represent the most prominent and recent paradigm shift in artificial intelligence. Foundation models are large models, trained on broad data that deliver high accuracy in many downstream tasks, often without fine-tuning.…

Cryptography and Security · Computer Science 2025-09-15 Hondamunige Prasanna Silva , Federico Becattini , Lorenzo Seidenari

Personalized Large Language Models (LLMs) have become increasingly prevalent, showcasing the impressive capabilities of models like GPT-4. This trend has also catalyzed extensive research on deploying LLMs on mobile devices. Feasible…

Machine Learning · Computer Science 2025-01-13 Yunmeng Shu , Shaofeng Li , Tian Dong , Yan Meng , Haojin Zhu

Backdoor attack is a new AI security risk that has emerged in recent years. Drawing on the previous research of adversarial attack, we argue that the backdoor attack has the potential to tap into the model learning process and improve model…

Cryptography and Security · Computer Science 2022-02-23 Shangxi Wu , Qiuyang He , Yi Zhang , Jitao Sang

Recently, diffusion models have become popular tools for image synthesis because of their high-quality outputs. However, like other large-scale models, they may leak private information about their training data. Here, we demonstrate a…

Machine Learning · Computer Science 2023-12-11 Shuai Tang , Zhiwei Steven Wu , Sergul Aydore , Michael Kearns , Aaron Roth