Privacy Threat

Privacy threats in machine learning, particularly within federated learning and large language models, are a significant area of concern, focusing on the risk of data leakage and model manipulation. Current research investigates various attack vectors, including membership inference attacks, poisoning attacks, and gradient-based data reconstruction, across diverse model architectures like graph neural networks and stable diffusion models. Understanding and mitigating these vulnerabilities is crucial for ensuring the responsible development and deployment of machine learning systems, impacting both the trustworthiness of AI and the protection of sensitive user data.

Papers

September 30, 2024

Comments on "Privacy-Enhanced Federated Learning Against Poisoning Adversaries"
Thomas Schneider, Ajith Suresh, Hossein Yalame
Federated Learning Poisoning Attack Homomorphic Encryption Private Federated Learning Online Comment Privacy Threat Privacy Framework

September 27, 2024

In-depth Analysis of Privacy Threats in Federated Learning for Medical Data
Badhan Chandra Das, M. Hadi Amini, Yanzhao Wu
Medical Image Privacy Risk Medical Data Depth Analysis Sensitive Patient Private Training Privacy Threat

August 23, 2024

LLM-PBE: Assessing Data Privacy in Large Language Models
Qinbin Li, Junyuan Hong, Chulin Xie, Jeffrey Tan, Rachel Xin, Junyi Hou, Xavier Yin, Zhun Wang, Dan Hendrycks, Zhangyang Wang, Bo Li, Bingsheng He, Dawn Song
Data Privacy LLM Evaluation Language Data Privacy Threat

July 25, 2024

Privacy Threats and Countermeasures in Federated Learning for Internet of Things: A Systematic Review
Adel ElZemity, Budi Arief
Differential Privacy Systematic Review Internet of Thing Device Inference Attack Rapid Countermeasure Internet of Thing Environment Privacy Threat

July 1, 2024

Unveiling the Unseen: Exploring Whitebox Membership Inference through the Lens of Explainability
Chenxi Li, Abhinav Kumar, Zhen Guo, Jie Hou, Reza Tourani
High Explainability Membership Inference Attack Camera Lens Unseen Video Privacy Threat Neural Information Box Membership Inference Attack Explanation Guided

February 7, 2024

Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning
Marlon Tobaben, Hibiki Ito, Joonas Jälkö, Gauri Pradhan, Yuan He, Antti Honkela
Deep Learning Global Impact Membership Inference Attack Membership Inference Efficient Classification Membership Privacy Privacy Threat Dataset Level

February 6, 2024

A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspective
Lei Yu, Meng Han, Yiming Li, Changting Lin, Yao Zhang, Mingyang Zhang, Yan Liu, Haiqin Weng, Yuseok Jeon, Ka-Ho Chow, Stacy Patterson
Timely Survey Federated Learning Vertical Federated Learning Privacy Risk Privacy Attack Privacy Threat

February 1, 2024

Survey of Privacy Threats and Countermeasures in Federated Learning
Masahiro Hayashitani, Junki Mori, Isamu Teranishi
Timely Survey Vertical Federated Learning Empirical Privacy Rapid Countermeasure Privacy Threat

January 25, 2024

Decentralized Federated Learning: A Survey on Security and Privacy
Ehsan Hallaji, Roozbeh Razavi-Far, Mehrdad Saif, Boyu Wang, Qiang Yang
Timely Survey Privacy Preserving Privacy Policy Blockchain Based Platform Security Related Decentralized Federated Learning Privacy Threat

December 29, 2023

AIJack: Let's Hijack AI! Security and Privacy Risk Simulator for Machine Learning
Hideaki Takahashi
Machine Learning Machine Learning Model Security Related Privacy Risk Privacy Threat Hijacking Task

November 15, 2023

Privacy Threats in Stable Diffusion Models
Thomas Cilloni, Charles Fleming, Charles Walter
Diffusion Model Membership Inference Attack Stable Diffusion Stable Diffusion Model Robust Defense Privacy Threat

November 7, 2023

When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers via Membership Inference Attacks
Huan Tian, Guangsheng Zhang, Bo Liu, Tianqing Zhu, Ming Ding, Wanlei Zhou
Procedural Fairness Membership Inference Attack Privacy Policy Model Fairness Fairness Method Privacy Threat

July 25, 2023

Node Injection Link Stealing Attack
Oualid Zari, Javier Parra-Arnau, Ayşe Ünsal, Melek Önen
Graph Neural Network Differential Privacy Privacy Threat Node Injection

April 6, 2023

Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding
Yuke Hu, Wei Liang, Ruofan Wu, Kai Xiao, Weiqiang Wang, Xiaochen Li, Jinfei Liu, Zhan Qin
Knowledge Graph Inference Attack Privacy Threat Federated Knowledge Graph Private Selection

February 1, 2022

Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification
Yuxin Wen, Jonas Geiping, Liam Fowl, Micah Goldblum, Tom Goldstein
Information Extraction Model Agnostic Threat Model Privacy Threat ANGLEr Behavior User Data Gradient Scaling

Privacy Threat

Papers

Comments on "Privacy-Enhanced Federated Learning Against Poisoning Adversaries"

In-depth Analysis of Privacy Threats in Federated Learning for Medical Data

LLM-PBE: Assessing Data Privacy in Large Language Models

Privacy Threats and Countermeasures in Federated Learning for Internet of Things: A Systematic Review

Unveiling the Unseen: Exploring Whitebox Membership Inference through the Lens of Explainability

Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning

A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspective

Survey of Privacy Threats and Countermeasures in Federated Learning

Decentralized Federated Learning: A Survey on Security and Privacy

AIJack: Let's Hijack AI! Security and Privacy Risk Simulator for Machine Learning

Privacy Threats in Stable Diffusion Models

When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers via Membership Inference Attacks

Node Injection Link Stealing Attack

Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding

Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification