thu-coai / Targeted-Data-Extraction
Official Code for ACL 2023 paper: "Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation"
☆22Updated last year
Alternatives and similar repositories for Targeted-Data-Extraction:
Users that are interested in Targeted-Data-Extraction are comparing it to the libraries listed below
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022☆29Updated 2 years ago
- Official implementation of Privacy Implications of Retrieval-Based Language Models (EMNLP 2023). https://arxiv.org/abs/2305.14888☆35Updated 9 months ago
- ACL 2021 - Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble☆17Updated last year
- ☆42Updated last month
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆32Updated last year
- ☆21Updated last year
- ☆35Updated last year
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆48Updated 5 months ago
- ☆26Updated last year
- Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"☆33Updated 3 years ago
- ☆25Updated 6 months ago
- [TACL] Code for "Red Teaming Language Model Detectors with Language Models"☆19Updated last year
- codes for "Searching for an Effective Defender:Benchmarking Defense against Adversarial Word Substitution"☆31Updated last year
- Code for the paper "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models" (NAACL-…☆40Updated 3 years ago
- Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models☆27Updated last year
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆36Updated 8 months ago
- ☆24Updated 3 years ago
- For Certified Robustness to Text Adversarial Attacks by Randomized [MASK]☆15Updated 5 months ago
- ☆16Updated last week
- Natural Universal Trigger Search (NUTS)☆21Updated 3 years ago
- Code and data for paper "A Semantic Invariant Robust Watermark for Large Language Models" accepted by ICLR 2024.☆27Updated 4 months ago
- ☆23Updated last year
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆48Updated 11 months ago
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆79Updated 2 months ago
- ☆33Updated 5 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆78Updated 10 months ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆64Updated 6 months ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆88Updated 6 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☆23Updated last year