← Learning Types
Machine Learning › Learning Types ›

Privacy

363 directly classified papers

Papers per year

Papers

Faster Privacy Accounting via Evolving Discretization ICML 2022
A Joint Exponential Mechanism For Differentially Private Top-$k$ ICML 2022
Private Streaming SCO in $\ell_p$ geometry with Applications in High Dimensional Online Decision Making ICML 2022
Deduplicating Training Data Mitigates Privacy Risks in Language Models ICML 2022
Secure Quantized Training for Deep Learning ICML 2022
Differentially Private Maximal Information Coefficients ICML 2022
Private Adaptive Optimization with Side information ICML 2022
DeepHardMark: Towards Watermarking Neural Network Hardware AAAI 2022
Canary Extraction in Natural Language Understanding Models ACL 2022
An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models EMNLP 2022
One size does not fit all: Investigating strategies for differentially-private learning across NLP tasks EMNLP 2022
PrivateSNN: Privacy-Preserving Spiking Neural Networks AAAI 2022
Defending against Model Stealing via Verifying Embedded External Features AAAI 2022
A Fusion-Denoising Attack on InstaHide with Data Augmentation AAAI 2022
Subspace Differential Privacy AAAI 2022
Private Rank Aggregation in Central and Local Models AAAI 2022
Locally Private k-Means Clustering with Constant Multiplicative Approximation and Near-Optimal Additive Error AAAI 2022
Hard to Forget: Poisoning Attacks on Certified Machine Unlearning AAAI 2022
How Private Is Your RL Policy? An Inverse RL Based Analysis Framework AAAI 2022
Cosine Model Watermarking against Ensemble Distillation AAAI 2022
Interpretable Privacy Preservation of Text Representations Using Vector Steganography AAAI 2022
Sentence-level Privacy for Document Embeddings ACL 2022
Training Text-to-Text Transformers with Privacy Guarantees ACL 2022
Addressing Resource and Privacy Constraints in Semantic Parsing Through Data Augmentation ACL 2022
Adaptive Differential Privacy for Language Model Training ACL 2022