ftramer / LM_Memorization
Training data extraction on GPT-2
☆184Updated 2 years ago
Alternatives and similar repositories for LM_Memorization:
Users that are interested in LM_Memorization are comparing it to the libraries listed below
- ☆285Updated last month
- A codebase that makes differentially private training of transformers easy.☆171Updated 2 years ago
- Python package for measuring memorization in LLMs.☆149Updated 4 months ago
- Repo for arXiv preprint "Gradient-based Adversarial Attacks against Text Transformers"☆105Updated 2 years ago
- ☆72Updated 2 years ago
- A re-implementation of the "Extracting Training Data from Large Language Models" paper by Carlini et al., 2020☆35Updated 2 years ago
- A survey of privacy problems in Large Language Models (LLMs). Contains summary of the corresponding paper along with relevant code☆67Updated 10 months ago
- ☆128Updated last year
- The repository contains the code for analysing the leakage of personally identifiable (PII) information from the output of next word pred…☆90Updated 7 months ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆85Updated 10 months ago
- ☆18Updated 3 years ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆96Updated last month
- Code for watermarking language models☆76Updated 6 months ago
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022☆29Updated 2 years ago
- Code for the paper "Weight Poisoning Attacks on Pre-trained Models" (ACL 2020)☆141Updated 3 years ago
- [ACL 2023] Knowledge Unlearning for Mitigating Privacy Risks in Language Models☆80Updated 6 months ago
- codes for "Searching for an Effective Defender:Benchmarking Defense against Adversarial Word Substitution"☆31Updated last year
- An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)☆175Updated last year
- Official Repository for Dataset Inference for LLMs☆32Updated 8 months ago
- Differentially-private transformers using HuggingFace and Opacus☆133Updated 7 months ago
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆109Updated 11 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆78Updated 10 months ago
- ☆27Updated 4 years ago
- Bad Characters: Imperceptible NLP Attacks☆34Updated 11 months ago
- Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"☆33Updated 3 years ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆149Updated 10 months ago
- ☆42Updated last month
- ☆35Updated last year
- A one-stop repository for large language model (LLM) unlearning. Supports TOFU, MUSE and is an easily extensible framework for new datase…☆200Updated this week
- [ICLR'24 Spotlight] DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer☆39Updated 10 months ago