ethz-spylab / misleading-privacy-evalsLinks
Official code for "Evaluations of Machine Learning Privacy Defenses are Misleading" (https://arxiv.org/abs/2404.17399)
☆10Updated last year
Alternatives and similar repositories for misleading-privacy-evals
Users that are interested in misleading-privacy-evals are comparing it to the libraries listed below
Sorting:
- ☆22Updated 8 months ago
- [NeurIPS23 (Spotlight)] "Model Sparsity Can Simplify Machine Unlearning" by Jinghan Jia*, Jiancheng Liu*, Parikshit Ram, Yuguang Yao, Gao…☆77Updated last year
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆60Updated 11 months ago
- "In-Context Unlearning: Language Models as Few Shot Unlearners". Martin Pawelczyk, Seth Neel* and Himabindu Lakkaraju*; ICML 2024.☆28Updated last year
- ☆44Updated 6 months ago
- [ICLR'24 Spotlight] DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer☆45Updated last year
- ☆162Updated last month
- ☆42Updated last year
- ☆46Updated last year
- ☆19Updated last year
- Github repo for NeurIPS 2024 paper "Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models"☆18Updated last month
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆57Updated last year
- ☆25Updated 5 months ago
- Code and dataset for the paper: "Can Editing LLMs Inject Harm?"☆21Updated 9 months ago
- Codebase for decoding compressed trust.☆24Updated last year
- ☆22Updated 2 years ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆66Updated last month
- Implementaiton of "DiLM: Distilling Dataset into Language Model for Text-level Dataset Distillation" (accepted by NAACL2024 Findings)".☆23Updated 6 months ago
- [ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation…☆130Updated 3 months ago
- Data Valuation without Training of a Model, submitted to ICLR'23☆22Updated 2 years ago
- Python package for measuring memorization in LLMs.☆164Updated last month
- ☆57Updated 2 years ago
- A survey on harmful fine-tuning attack for large language model☆205Updated last week
- ☆105Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆64Updated 7 months ago
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆67Updated 6 months ago
- [ICLR 2024] Towards Elminating Hard Label Constraints in Gradient Inverision Attacks☆13Updated last year
- This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturba…☆29Updated 5 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆74Updated 7 months ago
- Official Repository for Dataset Inference for LLMs☆38Updated last year