conftrace_
← Application Areas
Machine Learning › Application Areas ›

Privacy

2,847 papers

Papers per year

18
172
532
'15
'20
'25

Papers

Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration EMNLP 2024
Large Language Models Can Be Contextual Privacy Protection Learners EMNLP 2024
Extracting Prompts by Inverting LLM Outputs EMNLP 2024
CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation EMNLP 2024
MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance EMNLP 2024
RAFT: Realistic Attacks to Fool Text Detectors EMNLP 2024
Revisiting the Robustness of Watermarking to Paraphrasing Attacks EMNLP 2024
User Inference Attacks on Large Language Models EMNLP 2024
Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion EMNLP 2024
Waterfall: Scalable Framework for Robust Text Watermarking and Provenance for LLMs EMNLP 2024
Generalizing Clinical De-identification Models by Privacy-safe Data Augmentation using GPT-4 EMNLP 2024
De-Identification of Sensitive Personal Data in Datasets Derived from IIT-CDIP EMNLP 2024
MarkLLM: An Open-Source Toolkit for LLM Watermarking EMNLP 2024
A Hassle-free Algorithm for Strong Differential Privacy in Federated Learning Systems EMNLP 2024
Prompt Leakage effect and mitigation strategies for multi-turn LLM Applications EMNLP 2024
Granularity is crucial when applying differential privacy to text: An investigation for neural machine translation EMNLP 2024
To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models EMNLP 2024
Privacy Evaluation Benchmarks for NLP Models EMNLP 2024
Rethinking Evaluation Methods for Machine Unlearning EMNLP 2024
Immunization against harmful fine-tuning attacks EMNLP 2024
Enhancing Byzantine-Resistant Aggregations with Client Embedding EMNLP 2024
SecureSQL: Evaluating Data Leakage of Large Language Models as Natural Language Interfaces to Databases EMNLP 2024
GuardEmb: Dynamic Watermark for Safeguarding Large Language Model Embedding Service Against Model Stealing Attack EMNLP 2024
Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation EMNLP 2024
CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code EMNLP 2024