← Application Areas
Machine Learning › Application Areas ›

Privacy

2794 directly classified papers

Papers per year

Papers

Enhancing Scalability of Metric Differential Privacy via Secret Dataset Partitioning and Benders Decomposition IJCAI 2024
Segmenting Watermarked Texts From Language Models NIPS 2024
Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models NIPS 2024
Membership Inference Attacks against Language Models via Neighbourhood Comparison ACL 2023
How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks ACL 2023
Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection ACL 2023
Generalized PTR: User-Friendly Recipes for Data-Adaptive Algorithms with Differential Privacy AISTATS 2023
IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks ACL 2023
Make Text Unlearnable: Exploiting Effective Patterns to Protect Personal Data ACL 2023
ETHICIST: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation ACL 2023
Differentially Private Adapters for Parameter Efficient Acoustic Modeling INTERSPEECH 2023
SaFER: A Robust and Efficient Framework for Fine-tuning BERT-based Classifier with Noisy Labels ACL 2023
Mnemonist: Locating Model Parameters that Memorize Training Examples UAI 2023
Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks Using an Incompetent Teacher AAAI 2023
CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation Loss CVPR 2023
Backdoor Cleansing With Unlabeled Data CVPR 2023
DoubleDeceiver: Deceiving the Speaker Verification System Protected by Spoofing Countermeasures INTERSPEECH 2023
CUDA: Convolution-Based Unlearnable Datasets CVPR 2023
The Dark Side of Dynamic Routing Neural Networks: Towards Efficiency Backdoor Injection CVPR 2023
Color Backdoor: A Robust Poisoning Attack in Color Space CVPR 2023
Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization CVPR 2023
Using Text Injection to Improve Recognition of Personal Identifiers in Speech INTERSPEECH 2023
Purifier: Defending Data Inference Attacks via Transforming Confidence Scores AAAI 2023
Complement Sparsification: Low-Overhead Model Pruning for Federated Learning AAAI 2023
Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards ICML 2023