← Application Areas
Machine Learning › Application Areas ›

Privacy

2794 directly classified papers

Papers per year

Papers

Dual Calibration-based Personalised Federated Learning IJCAI 2024
Automatic Detection and Labelling of Personal Data in Case Reports from the ECHR in Spanish: Evaluation of Two Different Annotation Approaches EACL 2024
Unlearning during Learning: An Efficient Federated Machine Unlearning Method IJCAI 2024
Undetectable Watermarks for Language Models COLT 2024
Enhancing Controlled Query Evaluation through Epistemic Policies IJCAI 2024
Sample-Optimal Locally Private Hypothesis Selection and the Provable Benefits of Interactivity COLT 2024
Lower Bounds for Differential Privacy Under Continual Observation and Online Threshold Queries COLT 2024
Data Ownership and Privacy in Personalized AI Models in Assistive Healthcare IJCAI 2024
Locally Private and Robust Multi-Armed Bandits NIPS 2024
Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature NIPS 2024
Label Leakage in Vertical Federated Learning: A Survey IJCAI 2024
Anonymization Through Substitution: Words vs Sentences ACL 2024
Transferable Embedding Inversion Attack: Uncovering Privacy Risks in Text Embeddings without Model Queries ACL 2024
Evaluating Differentially Private Synthetic Data Generation in High-Stakes Domains EMNLP 2024
PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding ACL 2024
Conformity, Confabulation, and Impersonation: Persona Inconstancy in Multi-Agent LLM Collaboration ACL 2024
Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression EMNLP 2024
Quantifying Unintended Memorization in BEST-RQ ASR Encoders INTERSPEECH 2024
ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization NIPS 2024
Preset-Voice Matching for Privacy Regulated Speech-to-Speech Translation Systems ACL 2024
Segmenting Watermarked Texts From Language Models NIPS 2024
Downstream Trade-offs of a Family of Text Watermarks EMNLP 2024
TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification ACL 2024
Generation and Evaluation of Synthetic Endoscopy Free-Text Reports with Differential Privacy ACL 2024
Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping INTERSPEECH 2024