Privacy

Steganography of Steganographic Networks AAAI 2023 Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks EMNLP 2023 TAN Without a Burn: Scaling Laws of DP-SGD ICML 2023 TextObfuscator: Making Pre-trained Language Model a Privacy Protector via Obfuscating Word Representations ACL 2023 Trade-Offs Between Fairness and Privacy in Language Modeling ACL 2023 Training Data Extraction From Pre-trained Language Models: A Survey ACL 2023 Transferable Unlearnable Examples ICLR 2023 Tunable Soft Prompts are Messengers in Federated Learning EMNLP 2023 Two-Stage Voice Anonymization for Enhanced Privacy Interspeech 2023 Watermarking PLMs on Classification Tasks by Combining Contrastive Learning with Weight Perturbation EMNLP 2023 XRand: Differentially Private Defense against Explanation-Guided Attacks AAAI 2023 A bounded-noise mechanism for differential privacy COLT 2022 An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models EMNLP 2022 Are Large Pre-Trained Language Models Leaking Your Personal Information? EMNLP 2022 Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks NeurIPS 2022 Automated speech tools for helping communities process restricted-access corpora for language revival efforts ACL 2022 Behind the Mask: Demographic bias in name detection for PII masking ACL 2022 Bridging Central and Local Differential Privacy in Data Acquisition Mechanisms NeurIPS 2022 Bridging Differential Privacy and Byzantine-Robustness via Model Aggregation IJCAI 2022 Canary Extraction in Natural Language Understanding Models ACL 2022 Contribution-Aware Federated Learning for Smart Healthcare AAAI 2022 DeepAuth: A DNN Authentication Framework by Model-Unique and Fragile Signature Embedding AAAI 2022 DeepHardMark: Towards Watermarking Neural Network Hardware AAAI 2022 Differentially Private Instance Encoding against Privacy Attacks NAACL 2022 Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation EMNLP 2022