English
Related papers

Related papers: Label-only Model Inversion Attack: The Attack that…

200 papers

Removing information from a machine learning model is a non-trivial task that requires to partially revert the training process. This task is unavoidable when sensitive data, such as credit card numbers or passwords, accidentally enter the…

Machine Learning · Computer Science 2023-08-08 Alexander Warnecke , Lukas Pirch , Christian Wressnegger , Konrad Rieck

The purpose of anonymizing structured data is to protect the privacy of individuals in the data while retaining the statistical properties of the data. An important class of attack on anonymized data is attribute inference, where an…

Cryptography and Security · Computer Science 2025-07-03 Paul Francis , David Wagner

Text classification has become widely used in various natural language processing applications like sentiment analysis. Current applications often use large transformer-based language models to classify input texts. However, there is a lack…

Computation and Language · Computer Science 2022-09-22 Ruisi Zhang , Seira Hidano , Farinaz Koushanfar

This study investigates the privacy risks associated with text embeddings, focusing on the scenario where attackers cannot access the original embedding model. Contrary to previous research requiring direct model access, we explore a more…

Cryptography and Security · Computer Science 2025-01-15 Yu-Hsiang Huang , Yuche Tsai , Hsiang Hsiao , Hong-Yi Lin , Shou-De Lin

Few-shot learning arises in important practical scenarios, such as when a natural language understanding system needs to learn new semantic labels for an emerging, resource-scarce domain. In this paper, we explore retrieval-based methods…

Computation and Language · Computer Science 2021-04-14 Dian Yu , Luheng He , Yuan Zhang , Xinya Du , Panupong Pasupat , Qi Li

Semi-supervised learning methods can train high-accuracy machine learning models with a fraction of the labeled training samples required for traditional supervised learning. Such methods do not typically involve close review of the…

Machine Learning · Computer Science 2022-12-07 Marissa Connor , Vincent Emanuele

Gradient inversion (GI) attacks present a threat to the privacy of clients in federated learning (FL) by aiming to enable reconstruction of the clients' data from communicated model updates. A number of such techniques attempts to…

Machine Learning · Computer Science 2024-05-03 Huancheng Chen , Haris Vikalo

Recently, reconstruction-based anomaly detection was proposed as an effective technique to detect attacks in dynamic industrial control networks. Unlike classical network anomaly detectors that observe the network traffic,…

Cryptography and Security · Computer Science 2020-10-13 Alessandro Erba , Riccardo Taormina , Stefano Galelli , Marcello Pogliani , Michele Carminati , Stefano Zanero , Nils Ole Tippenhauer

Machine Unlearning (MU) aims to update Machine Learning (ML) models following requests to remove training samples and their influences on a trained model efficiently without retraining the original ML model from scratch. While MU itself has…

Machine Learning · Computer Science 2025-10-29 Liou Tang , James Joshi , Ashish Kundu

Two-party split learning is a popular technique for learning a model across feature-partitioned data. In this work, we explore whether it is possible for one party to steal the private label information from the other party during split…

Machine Learning · Computer Science 2022-05-26 Oscar Li , Jiankai Sun , Xin Yang , Weihao Gao , Hongyi Zhang , Junyuan Xie , Virginia Smith , Chong Wang

We design blackbox transfer-based targeted adversarial attacks for an environment where the attacker's source model and the target blackbox model may have disjoint label spaces and training datasets. This scenario significantly differs from…

Machine Learning · Computer Science 2021-03-19 Nathan Inkawhich , Kevin J Liang , Jingyang Zhang , Huanrui Yang , Hai Li , Yiran Chen

Machine learning models can leak information regarding the dataset they have trained. In this paper, we present the first membership inference attack against black-boxed object detection models that determines whether the given data records…

Computer Vision and Pattern Recognition · Computer Science 2020-01-29 Yeachan Park , Myungjoo Kang

Deep learning on graph structures has shown exciting results in various applications. However, few attentions have been paid to the robustness of such models, in contrast to numerous research work for image or text adversarial attack and…

Machine Learning · Computer Science 2018-06-08 Hanjun Dai , Hui Li , Tian Tian , Xin Huang , Lin Wang , Jun Zhu , Le Song

We consider the hard label based black box adversarial attack setting which solely observes predicted classes from the target model. Most of the attack methods in this setting suffer from impractical number of queries required to achieve a…

Machine Learning · Computer Science 2024-03-12 Jeonghwan Park , Paul Miller , Niall McLaughlin

Previous studies have verified that the functionality of black-box models can be stolen with full probability outputs. However, under the more practical hard-label setting, we observe that existing methods suffer from catastrophic…

Computer Vision and Pattern Recognition · Computer Science 2022-09-27 Yixu Wang , Jie Li , Hong Liu , Yan Wang , Yongjian Wu , Feiyue Huang , Rongrong Ji

Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can reach within a few percentage points of fully-supervised training,…

Machine Learning · Computer Science 2021-08-11 Nicholas Carlini

Backdoor attacks pose a new threat to NLP models. A standard strategy to construct poisoned data in backdoor attacks is to insert triggers (e.g., rare words) into selected sentences and alter the original label to a target label. This…

Computation and Language · Computer Science 2022-04-28 Leilei Gan , Jiwei Li , Tianwei Zhang , Xiaoya Li , Yuxian Meng , Fei Wu , Yi Yang , Shangwei Guo , Chun Fan

Model Inversion Attacks (MIAs) pose a significant threat to data privacy by reconstructing sensitive training samples from the knowledge embedded in trained machine learning models. Despite recent progress in enhancing the effectiveness of…

Cryptography and Security · Computer Science 2025-12-03 Hongyao Yu , Yixiang Qiu , Hao Fang , Tianqu Zhuang , Bin Chen , Sijin Yu , Bin Wang , Shu-Tao Xia , Ke Xu

Backdoor attacks pose a significant security vulnerability for deep neural networks (DNNs), enabling them to operate normally on clean inputs but manipulate predictions when specific trigger patterns occur. Currently, post-training backdoor…

Cryptography and Security · Computer Science 2024-10-22 Yanghao Su , Jie Zhang , Ting Xu , Tianwei Zhang , Weiming Zhang , Nenghai Yu

Influence estimation tools -- such as memorization scores -- are widely used to understand model behavior, attribute training data, and inform dataset curation. However, recent applications in data valuation and responsible machine learning…

Machine Learning · Computer Science 2025-09-30 Tue Do , Varun Chandrasekaran , Daniel Alabi