# TIPRDC: Task-Independent Privacy-Respecting Data Crowdsourcing Framework for Deep Learning with Anonymized Intermediate Representations

arXiv: https://arxiv.org/abs/2005.11480 · HTML: https://mlsanity.com/paper/2005.11480/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2020.

## Built on by (most cited first, 17 of 17)

- [No Free Lunch Theorem for Security and Utility in Federated Learning](https://mlsanity.com/paper/2203.05816/) (2022)
- [Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspective](https://mlsanity.com/paper/2107.01475/) (2021)
- [You Don't Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers' Private Personas](https://mlsanity.com/paper/2205.10228/) (2022)
- [Covert Model Poisoning Against Federated Learning: Algorithm Design and Optimization](https://mlsanity.com/paper/2101.11799/) (2021)
- [Decouple-and-Sample: Protecting sensitive information in task agnostic data release](https://mlsanity.com/paper/2203.13204/) (2022)
- [Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approach](https://mlsanity.com/paper/2403.01268/) (2024)
- [PriMask: Cascadable and Collusion-Resilient Data Masking for Mobile Cloud Inference](https://mlsanity.com/paper/2211.06716/) (2022)
- [Roulette: A Semantic Privacy-Preserving Device-Edge Collaborative Inference Framework for Deep Learning Classification Tasks](https://mlsanity.com/paper/2309.02820/) (2023)
- [Crafter: Facial Feature Crafting against Inversion-based Identity Theft on Deep Models](https://mlsanity.com/paper/2401.07205/) (2024)
- [Blinder: End-to-end Privacy Protection in Sensing Systems via Personalized Federated Learning](https://mlsanity.com/paper/2209.12046/) (2022)
- [Adjustable Privacy using Autoencoder-based Learning Structure](https://mlsanity.com/paper/2304.03538/) (2023)
- [PrivDiffuser: Privacy-Guided Diffusion Model for Data Obfuscation in Sensor Networks](https://mlsanity.com/paper/2412.14499/) (2024)
- [Diffusion-aided Task-oriented Semantic Communications with Model Inversion Attack](https://mlsanity.com/paper/2506.19886/) (2025)
- [MetaMorphosis: Task-oriented Privacy Cognizant Feature Generation for Multi-task Learning](https://mlsanity.com/paper/2305.07815/) (2023)
- [Protecting Activity Sensing Data Privacy Using Hierarchical Information Dissociation](https://mlsanity.com/paper/2409.03796/) (2024)
- [Nosy Layers, Noisy Fixes: Tackling DRAs in Federated Learning Systems using Explainable AI](https://mlsanity.com/paper/2505.10942/) (2025)
- [CLOAK: Contrastive Guidance for Latent Diffusion-Based Data Obfuscation](https://mlsanity.com/paper/2512.12086/) (2025)

## Abstract (arXiv)

The success of deep learning partially benefits from the availability of various large-scale datasets. These datasets are often crowdsourced from individual users and contain private information like gender, age, etc. The emerging privacy concerns from users on data sharing hinder the generation or use of crowdsourcing datasets and lead to hunger of training data for new deep learning applications. One na"ive solution is to pre-process the raw data to extract features at the user-side, and then only the extracted features will be sent to the data collector. Unfortunately, attackers can still exploit these extracted features to train an adversary classifier to infer private attributes. Some prior arts leveraged game theory to protect private attributes. However, these defenses are designed for known primary learning tasks, the extracted features work poorly for unknown learning tasks. To tackle the case where the learning task may be unknown or changing, we present TIPRDC, a task-independent privacy-respecting data crowdsourcing framework with anonymized intermediate representation. The goal of this framework is to learn a feature extractor that can hide the privacy information from the intermediate representations; while maximally retaining the original information embedded in the raw data for the data collector to accomplish unknown learning tasks. We design a hybrid training method to learn the anonymized intermediate representation: (1) an adversarial training process for hiding private information from features; (2) maximally retain original information using a neural-network-based mutual information estimator.