This repository provides a list a list of publications from DASHLab about ML privacy.
Our published papers that related to privacy-preserving.
2022: PTD: Privacy-Preserving Human Face Processing Framework using Tensor Decomposition accepted by ACM-SAC22. [paper]
2022: STL-DP: Differentially Private Time Series Exploring Decomposition and Compression Methods accepted by CIKM22. [paper]
Implementation and research on related papers.
Image generation using Differential Privacy [Link]
Image classification using Differential Privacy [Link]
Our published papers that related to machine-unlearning and generation-suppression.
2024: Disrupting Diffusion-based Inpainters with Semantic Digression accepted by IJCAI24. [paper]
2024: All but One: Surgical Concept Erasing with Model Preservation in Text-to-Image Diffusion Models accepted by AAAI24. [paper]
2024: Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge Distillation accepted by AAAI24. [paper]
2023: UNDO: Effective and Accurate Unlearning Method for Deep Neural Networks accepted by CIKM23. [paper]
2022: Efficient Two-stage Model Retraining for Machine Unlearning accepted by CVPR22. [paper]
2022-2026. 개인정보보호 관련 정책 변화를 유연하게 반영하여 준수하는 AI플랫폼 연구 및 개발 (IITP)