← Application Areas

Machine Learning › Application Areas ›

Privacy

2794 directly classified papers

Papers per year

Papers

Decomposing Prompts, Composing Actions: A Multi-Granularity Prompting Approach for Incremental Action Learning AAAI 2026

FiMMIA: scaling semantic perturbation-based membership inference across modalities EACL 2026

NRGMark: Localized Watermarking for Energy Transparency in Images WACV 2026

BAFLE-DCT: Bypassing Adversarial Filters via Frequency-Selective Embedding in the DCT Domain WACV 2026

Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening WACV 2026

When Flores Bloomz Wrong: Cross-Direction Contamination in Machine Translation Evaluation EACL 2026

Personal Information Parroting in Language Models EACL 2026

CodeGuard: Improving LLM Guardrails in CS Education EACL 2026

Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code EACL 2026

NLP Privacy Risk Identification in Social Media (NLP-PRISM): A Survey EACL 2026

PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing EACL 2026

DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP Protection EACL 2026

AFL-PRF: Adaptive Federated Learning for Low-Quality Data: Enhancing Performance, Robustness, and Fairness WACV 2026

FedEFC: Federated Learning Using Enhanced Forward Correction Against Noisy Labels WACV 2026

AEON: Adaptive Embedding Optimized Noise for Robust Watermarking in Diffusion Models WACV 2026

Personalized Image Privacy Advisors via Federated Daisy-Chaining WACV 2026

CLUE: Bringing Machine Unlearning to Mobile Devices WACV 2026

Marshaled Learning: Bridging Large Neural Networks with Memory-Constrained Trusted Execution Environments in Federated Learning WACV 2026

Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information WACV 2026

OpenLVLM-MIA: A Controlled Benchmark Revealing the Limits of Membership Inference Attacks on Large Vision-Language Models WACV 2026

Multi-Token Completion for Text Anonymization EACL 2026

Towards Fair and Efficient De-identification: Quantifying the Efficiency and Generalizability of De-identification Approaches EACL 2026

Reverse Personalization WACV 2026

Synthetic Doctor-Patient Dialogue Generation for Robust Medical ASR: A Scalable Pipeline for Vocabulary Expansion and Privacy Preservation EACL 2026

Detecting Training Data of Large Language Models via Expectation Maximization EACL 2026