jeffhj / LM_PersonalInfoLeak
The code and data for "Are Large Pre-Trained Language Models Leaking Your Personal Information?" (Findings of EMNLP '22)
☆19Updated last year
Related projects: ⓘ
- Official Repository for Dataset Inference for LLMs☆21Updated last month
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022☆26Updated 2 years ago
- ☆17Updated 2 years ago
- ☆10Updated 3 years ago
- ☆11Updated last year
- Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆55Updated 8 months ago
- ☆29Updated 10 months ago
- ☆47Updated 3 months ago
- IPython notebook with synthetic experiments for AFLite, based on the ICML 2020 paper, "Adversarial Filters of Dataset Biases".☆17Updated 4 years ago
- ☆19Updated last year
- A2T: Towards Improving Adversarial Training of NLP Models (EMNLP 2021 Findings)☆23Updated 3 years ago
- ☆37Updated 10 months ago
- ☆47Updated last year
- Explaining neural decisions contrastively to alternative decisions.☆23Updated 3 years ago
- ☆30Updated last year
- ☆23Updated 3 years ago
- ☆28Updated 3 years ago
- This is the official implementation for our ACL 2024 paper: "Causal Estimation of Memorisation Profiles".☆12Updated last week
- A re-implementation of the "Extracting Training Data from Large Language Models" paper by Carlini et al., 2020☆30Updated 2 years ago
- TextHide: Tackling Data Privacy in Language Understanding Tasks☆30Updated 3 years ago
- ☆30Updated last year
- Official implementation of Privacy Implications of Retrieval-Based Language Models (EMNLP 2023). https://arxiv.org/abs/2305.14888☆36Updated 3 months ago
- Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversaria…☆32Updated last year
- Code for preprint: Summarizing Differences between Text Distributions with Natural Language☆39Updated last year
- Implementation for Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder (EMNLP-Findings 2020)☆15Updated 3 years ago
- Code for "Universal Adversarial Triggers Are Not Universal."☆15Updated 4 months ago
- ☆23Updated 4 months ago
- ☆25Updated 2 years ago
- ☆17Updated 3 years ago
- [NeurIPS 2023 D&B Track] Code and data for paper "Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evalua…☆26Updated last year