Privacy

Amplifying Membership Exposure via Data Poisoning NeurIPS 2022 An Attention-Based Method for Guiding Attribute-Aligned Speech Representation Learning Interspeech 2022 An Embarrassingly Simple Approach for Intellectual Property Rights Protection on Recurrent Neural Networks AACL 2022 An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models EMNLP 2022 Anonymized Histograms in Intermediate Privacy Models NeurIPS 2022 Application for Real-time Personalized Speaker Extraction Interspeech 2022 APRIL: Finding the Achilles' Heel on Privacy for Vision Transformers CVPR 2022 A Private and Computationally-Efficient Estimator for Unbounded Gaussians COLT 2022 ARCANE: An Efficient Architecture for Exact Machine Unlearning IJCAI 2022 Archimedes Meets Privacy: On Privately Estimating Quantiles in High Dimensions Under Minimal Assumptions NeurIPS 2022 Are disentangled representations all you need to build speaker anonymization systems? Interspeech 2022 Are Large Pre-Trained Language Models Leaking Your Personal Information? EMNLP 2022 A Study of Face Obfuscation in ImageNet ICML 2022 A Study of the Attention Abnormality in Trojaned BERTs NAACL 2022 A Survey on Gradient Inversion: Attacks, Defenses and Future Directions IJCAI 2022 Asymptotically Optimal Locally Private Heavy Hitters via Parameterized Sketches AISTATS 2022 Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage CVPR 2022 Autoregressive Perturbations for Data Poisoning NeurIPS 2022 Backdoor Attacks on Self-Supervised Learning CVPR 2022 Backdoor Defense via Decoupling the Training Process ICLR 2022 BagFlip: A Certified Defense Against Data Poisoning NeurIPS 2022 Balancing utility and scalability in metric differential privacy UAI 2022 Bandits for Structure Perturbation-Based Black-Box Attacks To Graph Neural Networks With Theoretical Guarantees CVPR 2022 Bayesian Framework for Gradient Leakage ICLR 2022 Bayesian Pseudo Posterior Mechanism under Asymptotic Differential Privacy JMLR 2022