microsoft / dp-few-shot-generation
☆21Updated 9 months ago
Related projects: ⓘ
- [ICLR'24 Spotlight] DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer☆28Updated 3 months ago
- Official repo for the paper: Recovering Private Text in Federated Learning of Language Models (in NeurIPS 2022)☆56Updated last year
- ☆37Updated 10 months ago
- [ICML 2024] Differentially Private Synthetic Data via Foundation Model APIs 2: Text☆24Updated 2 months ago
- ☆17Updated 2 years ago
- A toolkit to assess data privacy in LLMs (under development)☆36Updated 2 weeks ago
- ☆19Updated last year
- Private Adaptive Optimization with Side Information (ICML '22)☆16Updated 2 years ago
- ☆21Updated last year
- ☆61Updated 2 years ago
- ☆10Updated 2 years ago
- ☆18Updated last week
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆32Updated 2 months ago
- ☆47Updated last year
- ☆63Updated 10 months ago
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models"☆12Updated last week
- ☆23Updated 4 months ago
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022☆26Updated 2 years ago
- Differentially-private transformers using HuggingFace and Opacus☆108Updated 3 weeks ago
- ☆11Updated last year
- A survey of privacy problems in Large Language Models (LLMs). Contains summary of the corresponding paper along with relevant code☆58Updated 3 months ago
- The repository contains the code for analysing the leakage of personally identifiable (PII) information from the output of next word pred…☆79Updated last month
- ☆10Updated 3 years ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents"☆29Updated 3 months ago
- ☆30Updated last year
- Python package for measuring memorization in LLMs.☆107Updated this week
- ☆37Updated 3 months ago
- ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆14Updated 2 weeks ago
- ☆26Updated last year
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆34Updated 4 months ago