Privacy Policy

Privacy policies, crucial for informing users about data handling practices and ensuring regulatory compliance, are the subject of intense research focusing on improving their clarity, accessibility, and automated analysis. Current efforts leverage techniques like natural language processing, large language models, and logic-based representations to enhance policy comprehension and compliance audits, while also exploring the interplay between privacy, fairness, and utility in machine learning models. This research is vital for promoting transparency and accountability in data practices, impacting both regulatory oversight and the development of trustworthy AI systems.

Papers

January 22, 2024

Lightweight Protection for Privacy in Offloaded Speech Understanding
Dongqi Cai
Privacy Policy Speech Signal Lightweight High Encoder Side

January 16, 2024

Calpric: Inclusive and Fine-grain Labeling of Privacy Policies with Crowdsourcing and Active Learning
Wenjun Qiu, David Lie, Lisa Austin
Fine Grained Training Data Active Learning Privacy Policy Crowdsourcing Context Amazon Mechanical Turk Privacy Label

January 2, 2024

PPBFL: A Privacy Protected Blockchain-based Federated Learning Model
Yang Li, Chunhe Xia, Wanshuang Lin, Tianbo Wang
Federated Learning Privacy Policy Blockchain Based Platform Differential Privacy Noise Adaptive Differential Privacy

January 1, 2024

Facebook Report on Privacy of fNIRS data
Md Imran Hossen, Sai Venkatesh Chilukoti, Liqun Shan, Vijay Srinivas Tida, Xiali Hei
Differential Privacy Privacy Policy Private Datasets Functional Near Infrared Spectroscopy

December 31, 2023

Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners
Rachel Redberg, Antti Koskela, Yu-Xiang Wang
Privacy Policy Practical Application Privacy Protection Private Stochastic Gradient Descent Privacy Preserving Machine Learning Privacy Analysis Private Linear

December 24, 2023

An Empirical Study of Efficiency and Privacy of Federated Learning Algorithms
Sofia Zahri, Hajar Bennouri, Ahmed M. Abdelmoniem
High Efficiency Differential Privacy Empirical Study Privacy Policy Secure Aggregation Internet of Thing Network Privacy Preserving Machine Learning Federated Learning Algorithm

December 22, 2023

December 20, 2023

December 5, 2023

Auto DP-SGD: Dual Improvements of Privacy and Accuracy via Automatic Clipping Threshold and Noise Multiplier Estimation
Sai Venkatesh Chilukoti, Md Imran Hossen, Liqun Shan, Vijay Srinivas Tida, Xiai Hei
Privacy Policy Noise Estimation Dp SGD Adaptive Clipping

December 4, 2023

A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly
Yifan Yao, Jinhao Duan, Kaidi Xu, Yuanfang Cai, Zhibo Sun, Yue Zhang
Large Language Model Timely Survey Medical LLM Privacy Policy Security Related Security Vulnerability Extraction Attack Inherent Vulnerability

November 30, 2023

Toward the Tradeoffs between Privacy, Fairness and Utility in Federated Learning
Kangkang Sun, Xiaojin Zhang, Xi Lin, Gaolei Li, Jing Wang, Jianhua Li
Procedural Fairness Privacy Policy Task Utility Fairness Metric Fair Model Fair Federated Learning

November 9, 2023

The Paradox of Noise: An Empirical Study of Noise-Infusion Mechanisms to Improve Generalization, Stability, and Privacy in Federated Learning
Elaheh Jafarigol, Theodore Trafalis
Deep Learning Strong Generalization Industrial Disturbing Noise Privacy Policy Federated Learning Framework Additive Noise Noise Injection

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

October 28, 2023

Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning
Zheyuan Liu, Guangyao Dou, Yijun Tian, Chunhui Zhang, Eli Chien, Ziwei Zhu
High Efficiency Privacy Policy Machine Unlearning Unlearning Framework Task Utility Unlearning Method Privacy Utility Emotional Dilemma

October 24, 2023

On Responsible Machine Learning Datasets with Fairness, Privacy, and Regulatory Norms
Surbhi Mittal, Kartik Thakral, Richa Singh, Mayank Vatsa, Tamar Glaser, Cristian Canton Ferrer, Tal Hassner
Artificial Intelligence Procedural Fairness Privacy Policy Trustworthy Artificial Intelligence Responsible Machine Learning Normative System Dataset Documentation

October 22, 2023

Data-Free Distillation Improves Efficiency and Privacy in Federated Thorax Disease Analysis
Ming Li, Guang Yang
High Efficiency Privacy Policy Optimization Proxy Federated Distillation Free Distillation Thorax Disease

October 20, 2023

Salted Inference: Enhancing Privacy while Maintaining Efficiency of Split Inference in Mobile Computing
Mohammad Malekzadeh, Fahim Kawsar
Neural Network Privacy Policy Homomorphic Encryption Enhancing Efficiency Device Machine Learning Inference Module

October 17, 2023

Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning
Rui Wen, Tianhao Wang, Michael Backes, Yang Zhang, Ahmed Salem
Context Learning Privacy Policy Security Related Private Data Privacy Analysis LLM Adaptation Soft Prompt Tuning Model Stealing

Privacy Policy

Papers

Lightweight Protection for Privacy in Offloaded Speech Understanding

Calpric: Inclusive and Fine-grain Labeling of Privacy Policies with Crowdsourcing and Active Learning

PPBFL: A Privacy Protected Blockchain-based Federated Learning Model

Facebook Report on Privacy of fNIRS data

Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners

An Empirical Study of Efficiency and Privacy of Federated Learning Algorithms

Robustness, Efficiency, or Privacy: Pick Two in Machine Learning

SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learning

Enhancing Trade-offs in Privacy, Utility, and Computational Efficiency through MUltistage Sampling Technique (MUST)

Transparency and Privacy: The Role of Explainable AI and Federated Learning in Financial Fraud Detection

Auto DP-SGD: Dual Improvements of Privacy and Accuracy via Automatic Clipping Threshold and Noise Multiplier Estimation

A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly

Toward the Tradeoffs between Privacy, Fairness and Utility in Federated Learning

The Paradox of Noise: An Empirical Study of Noise-Infusion Mechanisms to Improve Generalization, Stability, and Privacy in Federated Learning

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

Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning

On Responsible Machine Learning Datasets with Fairness, Privacy, and Regulatory Norms

Data-Free Distillation Improves Efficiency and Privacy in Federated Thorax Disease Analysis

Salted Inference: Enhancing Privacy while Maintaining Efficiency of Split Inference in Mobile Computing

Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning