NLPExplorer

PrivateNLP - 2024

Total Papers:- 19

Total Papers accross all years:- 38

Total Citations :- 0

1 2 »

Anonymization Through Substitution: Words vs Sentences

PrivaT5: A Generative Language Model for Privacy Policies

Mohammad Zoubi | Santosh T.y.s.s | Edgar Rosas | Matthias Grabmair |

Noisy Neighbors: Efficient membership inference attacks against LLMs

Filippo Galli | Luca Melis | Tommaso Cucinotta |

Deconstructing Classifiers: Towards A Data Reconstruction Attack Against Text Classification Models

Adel Elmahdy | Ahmed Salem |

Improving Authorship Privacy: Adaptive Obfuscation with the Dynamic Selection of Techniques

Hemanth Kandula | Damianos Karakos | Haoling Qiu | Brian Ulicny |

Cloaked Classifiers: Pseudonymization Strategies on Sensitive Classification Tasks

Arij Riabi | Menel Mahamdi | Virginie Mouilleron | Djamé Seddah |

Don’t forget private retrieval: distributed private similarity search for large language models

Guy Zyskind | Tobin South | Alex Pentland |

Reinforcement Learning-Driven LLM Agent for Automated Attacks on LLMs

Characterizing Stereotypical Bias from Privacy-preserving Pre-Training

Stefan Arnold | Rene Gröbner | Annika Schreiner |

PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding

Preset-Voice Matching for Privacy Regulated Speech-to-Speech Translation Systems

Can LLMs get help from other LLMs without revealing private information?

Proceedings of the Fifth Workshop on Privacy in Natural Language Processing

PocketLLM: Enabling On-Device Fine-Tuning for Personalized LLMs

Dan Peng | Zhihui Fu | Jun Wang |