English
Related papers

Related papers: Preventing Inferences through Data Dependencies on…

200 papers

The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…

Machine Learning · Computer Science 2025-11-14 James Jin Kang , Dang Bui , Thanh Pham , Huo-Chong Ling

Deep neural networks are susceptible to various inference attacks as they remember information about their training data. We design white-box inference attacks to perform a comprehensive privacy analysis of deep learning models. We measure…

Machine Learning · Statistics 2020-06-09 Milad Nasr , Reza Shokri , Amir Houmansadr

Graph generative diffusion models have recently emerged as a powerful paradigm for generating complex graph structures, effectively capturing intricate dependencies and relationships within graph data. However, the privacy risks associated…

Machine Learning · Computer Science 2026-01-08 Xiuling Wang , Xin Huang , Guibo Luo , Jianliang Xu

Data poisoning is one of the most relevant security threats against machine learning and data-driven technologies. Since many applications rely on untrusted training data, an attacker can easily craft malicious samples and inject them into…

Cryptography and Security · Computer Science 2021-12-01 Nicolas M. Müller , Simon Roschmann , Konstantin Böttinger

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

We develop a data-driven framework for assessing the resilience of linear time-invariant systems against malicious false-data-injection sensor attacks. Leveraging sparse observability, we propose data-driven resilience metrics and derive…

Systems and Control · Electrical Eng. & Systems 2026-03-24 Takumi Shinohara , Karl Henrik Johansson , Henrik Sandberg

Property inference attacks consider an adversary who has access to the trained model and tries to extract some global statistics of the training data. In this work, we study property inference in scenarios where the adversary can…

Machine Learning · Computer Science 2021-01-28 Melissa Chase , Esha Ghosh , Saeed Mahloujifar

This paper studies the attack detection problem in a data-driven and model-free setting, for deterministic systems with linear and time-invariant dynamics. Differently from existing studies that leverage knowledge of the system dynamics to…

Systems and Control · Electrical Eng. & Systems 2020-03-19 Vishaal Krishnan , Fabio Pasqualetti

Federated learning is a technique that allows multiple entities to collaboratively train models using their data without compromising data privacy. However, despite its advantages, federated learning can be susceptible to false data…

Machine Learning · Computer Science 2024-01-17 Or Shalom , Amir Leshem , Waheed U. Bajwa

Sensitive inferences and user re-identification are major threats to privacy when raw sensor data from wearable or portable devices are shared with cloud-assisted applications. To mitigate these threats, we propose mechanisms to transform…

Machine Learning · Computer Science 2019-11-15 Mohammad Malekzadeh , Richard G. Clegg , Andrea Cavallaro , Hamed Haddadi

Deep Neural Networks (DNNs) are susceptible to model stealing attacks, which allows a data-limited adversary with no knowledge of the training dataset to clone the functionality of a target model, just by using black-box query access. Such…

Machine Learning · Statistics 2019-11-19 Sanjay Kariyappa , Moinuddin K Qureshi

Federated learning is considered as an effective privacy-preserving learning mechanism that separates the client's data and model training process. However, federated learning is still under the risk of privacy leakage because of the…

Machine Learning · Computer Science 2022-06-03 Yuxuan Wan , Han Xu , Xiaorui Liu , Jie Ren , Wenqi Fan , Jiliang Tang

In this paper, we investigate how attackers can discover sensitive information embedded within databases by exploiting inference rules. We demonstrate the inadequacy of naively applied existing state of the art differential privacy (DP)…

Cryptography and Security · Computer Science 2026-02-18 Yasmine Hayder , Adrien Boiret , Cédric Eichler , Benjamin Nguyen

Model stealing attack is increasingly threatening the confidentiality of machine learning models deployed in the cloud. Recent studies reveal that adversaries can exploit data synthesis techniques to steal machine learning models even in…

Cryptography and Security · Computer Science 2025-03-25 Yunfei Yang , Xiaojun Chen , Yuexin Xuan , Zhendong Zhao

The literature on differential privacy almost invariably assumes that the data to be analyzed are fully observed. In most practical applications this is an unrealistic assumption. A popular strategy to address this problem is imputation, in…

Databases · Computer Science 2022-07-15 Soumojit Das , Jorg Drechsler , Keith Merrill , Shawn Merrill

High-performance Deep Neural Networks (DNNs) are increasingly deployed in many real-world applications e.g., cloud prediction APIs. Recent advances in model functionality stealing attacks via black-box access (i.e., inputs in, predictions…

Machine Learning · Computer Science 2020-03-04 Tribhuvanesh Orekondy , Bernt Schiele , Mario Fritz

So far, privacy models follow two paradigms. The first paradigm, termed inferential privacy in this paper, focuses on the risk due to statistical inference of sensitive information about a target record from other records in the database.…

Databases · Computer Science 2012-02-17 Ke Wang , Peng Wang , Ada Waichee Fu , Raywong Chi-Wing Wong

Constant-time programming is a countermeasure to prevent cache based attacks where programs should not perform memory accesses that depend on secrets. In some cases this policy can be safely relaxed if one can prove that the program does…

Cryptography and Security · Computer Science 2023-06-22 Cristian Ene , Laurent Mounier , Marie-Laure Potet

Many damaging cybersecurity attacks are enabled when an attacker can access residual sensitive information (e.g. cryptographic keys, personal identifiers) left behind from earlier computation. Attackers can sometimes use residual…

Cryptography and Security · Computer Science 2021-06-21 Deborah Shands , Carolyn Talcott

Diffusion models have been remarkably successful in data synthesis. However, when these models are applied to sensitive datasets, such as banking and human face data, they might bring up severe privacy concerns. This work systematically…

Cryptography and Security · Computer Science 2024-04-30 Hailong Hu , Jun Pang