ethz-spylab / misleading-privacy-evals
Official code for "Evaluations of Machine Learning Privacy Defenses are Misleading" (https://arxiv.org/abs/2404.17399)
☆10Updated 11 months ago
Alternatives and similar repositories for misleading-privacy-evals:
Users that are interested in misleading-privacy-evals are comparing it to the libraries listed below
- ☆42Updated 2 months ago
- [ICLR'24 Spotlight] DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer☆39Updated 10 months ago
- This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)☆19Updated 7 months ago
- ☆26Updated last year
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆42Updated 5 months ago
- Github repo for NeurIPS 2024 paper "Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models"☆14Updated 6 months ago
- ☆20Updated 4 months ago
- ☆54Updated 2 years ago
- ☆21Updated last year
- This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturba…☆25Updated last month
- ☆21Updated last month
- ☆44Updated 8 months ago
- [NeurIPS23 (Spotlight)] "Model Sparsity Can Simplify Machine Unlearning" by Jinghan Jia*, Jiancheng Liu*, Parikshit Ram, Yuguang Yao, Gao…☆67Updated last year
- Codebase for decoding compressed trust.☆23Updated 11 months ago
- ☆19Updated last year
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆58Updated 6 months ago
- Official Repository for Dataset Inference for LLMs☆33Updated 9 months ago
- Likelihood Ratio Attack (LiRA) in PyTorch☆14Updated last month
- ☆44Updated 2 years ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆76Updated 3 weeks ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆46Updated 3 months ago
- The collection of papers about Private Evolution☆13Updated last week
- A toolkit to assess data privacy in LLMs (under development)☆57Updated 3 months ago
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆18Updated last year
- The official implement of paper "Does Federated Learning Really Need Backpropagation?"☆24Updated 2 years ago
- Implementaiton of "DiLM: Distilling Dataset into Language Model for Text-level Dataset Distillation" (accepted by NAACL2024 Findings)".☆18Updated 2 months ago
- This repo is for the safety topic, including attacks, defenses and studies related to reasoning and RL☆17Updated this week
- ☆21Updated 2 weeks ago
- Official code for SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆15Updated 2 weeks ago
- Private Evolution: Generating DP Synthetic Data without Training [ICLR 2024, ICML 2024 Spotlight]☆95Updated 2 months ago