Privacy

A Watermark for Large Language Models ICML 2023 Boundary Unlearning: Rapid Forgetting of Deep Networks via Shifting the Decision Boundary CVPR 2023 Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting ICML 2023 CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning ICLR 2023 Can Shadows Reveal Biometric Information? WACV 2023 CLIP2Protect: Protecting Facial Privacy Using Text-Guided Makeup via Adversarial Latent Search CVPR 2023 Copyright Violations and Large Language Models EMNLP 2023 Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models ICLR 2023 DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models EMNLP 2023 Differentially Private Condorcet Voting AAAI 2023 Differentially Private Learning with Per-Sample Adaptive Clipping AAAI 2023 Differential Privacy in Cooperative Multiagent Planning UAI 2023 Does Label Differential Privacy Prevent Label Inference Attacks? AISTATS 2023 Domain Specified Optimization for Deployment Authorization ICCV 2023 Echo of Neighbors: Privacy Amplification for Personalized Private Federated Learning with Shuffle Model AAAI 2023 ERASER: AdvERsArial Sensitive Element Remover for Image Privacy Preservation AAAI 2023 ERM-KTP: Knowledge-Level Machine Unlearning via Knowledge Transfer CVPR 2023 ETHICIST: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation ACL 2023 Extracting Robust Models with Uncertain Examples ICLR 2023 Federated Nearest Neighbor Machine Translation ICLR 2023 Flow-Based Robust Watermarking with Invertible Noise Layer for Black-Box Distortions AAAI 2023 Hiding Visual Information via Obfuscating Adversarial Perturbations ICCV 2023 Honeycomb: Secure and Efficient GPU Executions via Static Validation OSDI 2023 Individual Privacy Accounting with Gaussian Differential Privacy ICLR 2023 KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment ACL 2023