English
Related papers

Related papers: Reconstructing Training Data from Diverse ML Model…

200 papers

Current methods for reconstructing training data from trained classifiers are restricted to very small models, limited training set sizes, and low-resolution images. Such restrictions hinder their applicability to real-world scenarios. In…

Machine Learning · Computer Science 2024-07-23 Yakir Oz , Gilad Yehudai , Gal Vardi , Itai Antebi , Michal Irani , Niv Haim

Transfer learning is an important approach that produces pre-trained teacher models which can be used to quickly build specialized student models. However, recent research on transfer learning has found that it is vulnerable to various…

Cryptography and Security · Computer Science 2022-03-15 Dayong Ye , Huiqiang Chen , Shuai Zhou , Tianqing Zhu , Wanlei Zhou , Shouling Ji

Model Extraction Attacks (MEAs) threaten modern machine learning systems by enabling adversaries to steal models, exposing intellectual property and training data. With the increasing deployment of machine learning models in distributed…

Cryptography and Security · Computer Science 2025-02-25 Kaixiang Zhao , Lincan Li , Kaize Ding , Neil Zhenqiang Gong , Yue Zhao , Yushun Dong

Being able to reconstruct training data from the parameters of a neural network is a major privacy concern. Previous works have shown that reconstructing training data, under certain circumstances, is possible. In this work, we analyse such…

Federated learning is a decentralized learning paradigm introduced to preserve privacy of client data. Despite this, prior work has shown that an attacker at the server can still reconstruct the private training data using only the client…

Cryptography and Security · Computer Science 2024-03-28 Joshua C. Zhao , Ahaan Dabholkar , Atul Sharma , Saurabh Bagchi

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

This paper reveals a data bias issue that can severely affect the performance while conducting a machine learning model for malicious URL detection. We describe how such bias can be identified using interpretable machine learning…

Machine Learning · Computer Science 2024-02-12 YunDa Tsai , Cayon Liow , Yin Sheng Siang , Shou-De Lin

In recent years, semantic communication has been a popular research topic for its superiority in communication efficiency. As semantic communication relies on deep learning to extract meaning from raw messages, it is vulnerable to attacks…

Information Theory · Computer Science 2023-08-09 Yuhao Chen , Qianqian Yang , Zhiguo Shi , Jiming Chen

Machine unlearning is an emerging technique that aims to remove the influence of specific data from trained models, thereby enhancing privacy protection. However, recent research has uncovered critical privacy vulnerabilities, showing that…

Cryptography and Security · Computer Science 2026-01-29 Lulu Xue , Shengshan Hu , Wei Lu , Ziqi Zhou , Yufei Song , Jianhong Cheng , Minghui Li , Yanjun Zhang , Leo Yu Zhang

Modern deep neural networks are often vulnerable to adversarial samples. Based on the first optimization-based attacking method, many following methods are proposed to improve the attacking performance and speed. Recently, generation-based…

Computer Vision and Pattern Recognition · Computer Science 2019-08-15 Jiangfan Han , Xiaoyi Dong , Ruimao Zhang , Dongdong Chen , Weiming Zhang , Nenghai Yu , Ping Luo , Xiaogang Wang

Machine learning models are vulnerable to membership inference attacks in which an adversary aims to predict whether or not a particular sample was contained in the target model's training dataset. Existing attack methods have commonly…

Cryptography and Security · Computer Science 2022-09-01 Yiyong Liu , Zhengyu Zhao , Michael Backes , Yang Zhang

Model inversion, whose goal is to recover training data from a pre-trained model, has been recently proved feasible. However, existing inversion methods usually suffer from the mode collapse problem, where the synthesized instances are…

Artificial Intelligence · Computer Science 2021-05-19 Gongfan Fang , Jie Song , Xinchao Wang , Chengchao Shen , Xingen Wang , Mingli Song

Adversarial attacks have rendered high security risks on modern deep learning systems. Adversarial training can significantly enhance the robustness of neural network models by suppressing the non-robust features. However, the models often…

Machine Learning · Computer Science 2021-03-30 Yi Cai , Xuefei Ning , Huazhong Yang , Yu Wang

The widespread use of diffusion models has led to an abundance of AI-generated data, raising concerns about model collapse -- a phenomenon in which recursive iterations of training on synthetic data lead to performance degradation. Prior…

Machine Learning · Computer Science 2025-12-29 Lianghe Shi , Meng Wu , Huijie Zhang , Zekai Zhang , Molei Tao , Qing Qu

Machine Learning has been applied in a wide range of tasks throughout the last years, ranging from image classification to autonomous driving and natural language processing. Restricted Boltzmann Machine (RBM) has received recent attention…

Machine Learning · Computer Science 2021-01-05 Gustavo H. de Rosa , Mateus Roder , João P. Papa

The recovery of training data from generative models ("model inversion") has been extensively studied for diffusion models in the data domain as a memorization/overfitting phenomenon. Latent diffusion models (LDMs), which operate on the…

Machine Learning · Computer Science 2026-03-26 Mingxing Rao , Bowen Qu , Daniel Moyer

Generative AI technologies have been deployed in many places, such as (multimodal) large language models and vision generative models. Their remarkable performance should be attributed to massive training data and emergent reasoning…

Machine Learning · Computer Science 2024-07-31 Zheyuan Liu , Guangyao Dou , Zhaoxuan Tan , Yijun Tian , Meng Jiang

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

Deep learning has become the state of the art approach in many machine learning problems such as classification. It has recently been shown that deep learning is highly vulnerable to adversarial perturbations. Taking the camera systems of…

Machine Learning · Statistics 2018-02-09 Thilo Strauss , Markus Hanselmann , Andrej Junginger , Holger Ulmer

This work studies training generative adversarial networks under the federated learning setting. Generative adversarial networks (GANs) have achieved advancement in various real-world applications, such as image editing, style transfer,…

Machine Learning · Computer Science 2020-07-21 Chenyou Fan , Ping Liu