← Security & Privacy
Security & Privacy ›

Privacy

626 directly classified papers

Papers per year

Papers

A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network INTERSPEECH 2022
An Attention-Based Method for Guiding Attribute-Aligned Speech Representation Learning INTERSPEECH 2022
Not All Poisons are Created Equal: Robust Training against Data Poisoning ICML 2022
On Privacy and Personalization in Cross-Silo Federated Learning NIPS 2022
LAMP: Extracting Text from Gradients with Language Model Priors NIPS 2022
Triggerless Backdoor Attack for NLP Tasks with Clean Labels NAACL 2022
Privacy Preserving Partial Localization CVPR 2022
Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification ICML 2022
Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation ICML 2022
Secure Quantized Training for Deep Learning ICML 2022
Deduplicating Training Data Mitigates Privacy Risks in Language Models ICML 2022
GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing ICML 2022
Faster Privacy Accounting via Evolving Discretization ICML 2022
Backdoor Attacks in Federated Learning by Rare Embeddings and Gradient Ensembling EMNLP 2022
How reparametrization trick broke differentially-private text representation learning ACL 2022
THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption ACL 2022
Adaptive Differential Privacy for Language Model Training ACL 2022
MExMI: Pool-based Active Model Extraction Crossover Membership Inference NIPS 2022
Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attack NIPS 2022
Dataset Inference for Self-Supervised Models NIPS 2022
Measuring Data Reconstruction Defenses in Collaborative Inference Systems NIPS 2022
Learning to Generate Inversion-Resistant Model Explanations NIPS 2022
Amplifying Membership Exposure via Data Poisoning NIPS 2022
Revisiting Injective Attacks on Recommender Systems NIPS 2022
VoiceBlock: Privacy through Real-Time Adversarial Attacks with Audio-to-Audio Models NIPS 2022