← Application Areas
Machine Learning › Application Areas ›

Privacy

2794 directly classified papers

Papers per year

Papers

Exploring Query Efficient Data Generation Towards Data-Free Model Stealing in Hard Label Setting AAAI 2025
Re-identification of De-identified Documents with Autoregressive Infilling ACL 2025
Multimodal Pragmatic Jailbreak on Text-to-image Models ACL 2025
Sandcastles in the Storm: Revisiting the (Im)possibility of Strong Watermarking ACL 2025
Split Adaptation for Pre-trained Vision Transformers CVPR 2025
LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty CVPR 2025
RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis EMNLP 2025
Multi-Modal Recommendation Unlearning for Legal, Licensing, and Modality Constraints AAAI 2025
Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark EMNLP 2025
FedPIA – Permuting and Integrating Adapters Leveraging Wasserstein Barycenters for Finetuning Foundation Models in Multi-Modal Federated Learning AAAI 2025
DP-GTR: Differentially Private Prompt Protection via Group Text Rewriting EMNLP 2025
Not Every Token Needs Forgetting: Selective Unlearning Balancing Forgetting and Utility in Large Language Models EMNLP 2025
One VLM to Keep it Learning: Generation and Balancing for Data-Free Continual Visual Question Answering WACV 2025
Counterfactual Evaluation for Blind Attack Detection in LLM-based Evaluation Systems IJCNLP 2025
IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization IJCNLP 2025
With Privacy, Size Matters: On the Importance of Dataset Size in Differentially Private Text Rewriting IJCNLP 2025
Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning CVPR 2025
Watermarking with Low-Entropy POS-Guided Token Partitioning and Z-Score-Driven Dynamic Bias for Large Language Models EMNLP 2025
EntropyMark: Towards More Harmless Backdoor Watermark via Entropy-based Constraint for Open-source Dataset Copyright Protection CVPR 2025
LUME: LLM Unlearning with Multitask Evaluations EMNLP 2025
FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning CVPR 2025
Resource-Efficient Anonymization of Textual Data via Knowledge Distillation from Large Language Models COLING 2025
Indonesian Speech Content De-Identification in Low Resource Transcripts COLING 2025
Where's the Liability in the Generative Era? Recovery-based Black-Box Detection of AI-Generated Content CVPR 2025
Towards Operationalizing Right to Data Protection NAACL 2025