thu-coai / Targeted-Data-ExtractionLinks
Official Code for ACL 2023 paper: "Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation"
☆23Updated 2 years ago
Alternatives and similar repositories for Targeted-Data-Extraction
Users that are interested in Targeted-Data-Extraction are comparing it to the libraries listed below
Sorting:
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022☆29Updated 2 years ago
- ☆44Updated 4 months ago
- Official implementation of Privacy Implications of Retrieval-Based Language Models (EMNLP 2023). https://arxiv.org/abs/2305.14888☆35Updated last year
- ☆21Updated last year
- ☆21Updated 3 months ago
- ☆41Updated 8 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆29Updated 10 months ago
- ☆26Updated 9 months ago
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆33Updated last year
- ☆13Updated 2 years ago
- A2T: Towards Improving Adversarial Training of NLP Models (EMNLP 2021 Findings)☆26Updated 3 years ago
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆77Updated last month
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆36Updated 11 months ago
- ☆24Updated last year
- Code for the paper "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models" (NAACL-…☆41Updated 3 years ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆51Updated 8 months ago
- ☆36Updated 2 years ago
- Code and data for paper "A Semantic Invariant Robust Watermark for Large Language Models" accepted by ICLR 2024.☆32Updated 7 months ago
- [NeurIPS 2024 D&B] Evaluating Copyright Takedown Methods for Language Models☆17Updated 11 months ago
- Our research proposes a novel MoGU framework that improves LLMs' safety while preserving their usability.☆15Updated 5 months ago
- Restore safety in fine-tuned language models through task arithmetic☆28Updated last year
- [ACL2024-Main] Data and Code for WaterBench: Towards Holistic Evaluation of LLM Watermarks☆26Updated last year
- Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"☆33Updated 3 years ago
- ☆38Updated last year
- ☆25Updated 4 years ago
- ☆27Updated last year
- codes for "Searching for an Effective Defender:Benchmarking Defense against Adversarial Word Substitution"☆31Updated last year
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆59Updated 8 months ago
- [ICLR'24 Spotlight] DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer☆43Updated last year
- 🤫 Code and benchmark for our ICLR 2024 spotlight paper: "Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Con…☆42Updated last year