☆77May 31, 2023Updated 2 years ago
Alternatives and similar repositories for Intro_to_ML_Safety
Users that are interested in Intro_to_ML_Safety are comparing it to the libraries listed below
Sorting:
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆20Oct 18, 2024Updated last year
- ☆16Dec 9, 2023Updated 2 years ago
- ☆13Mar 22, 2023Updated 2 years ago
- Code for our paper "Localizing Lying in Llama"☆13Apr 24, 2025Updated 10 months ago
- Machine Learning for Alignment Bootcamp (MLAB).☆31Jan 24, 2022Updated 4 years ago
- [NeurIPS 2023] Differentially Private Image Classification by Learning Priors from Random Processes☆12Jun 12, 2023Updated 2 years ago
- Code for "Automatic Circuit Finding and Faithfulness"☆17Jul 11, 2024Updated last year
- Cross-library augmentation toolbox supporting 300 operators over 8 libraries + AI transforms☆12Jan 11, 2022Updated 4 years ago
- ☆37Feb 11, 2025Updated last year
- Work in progress! I don't recommend looking at the code right now.☆24Dec 3, 2025Updated 3 months ago
- A School for All Seasons on Trustworthy Machine Learning☆12Jun 30, 2021Updated 4 years ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆241Aug 11, 2025Updated 6 months ago
- This repository holds code and other relevant files for the NeurIPS 2022 tutorial: Foundational Robustness of Foundation Models.☆72Jan 13, 2023Updated 3 years ago
- Source code for "Neural Anisotropy Directions"☆16Nov 17, 2020Updated 5 years ago
- Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning [ICML 2024]☆21May 2, 2024Updated last year
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆38Jun 14, 2022Updated 3 years ago
- The Happy Faces Benchmark☆15Jul 20, 2023Updated 2 years ago
- Representation Engineering: A Top-Down Approach to AI Transparency☆957Aug 14, 2024Updated last year
- source for llmsec.net☆16Jul 24, 2024Updated last year
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆116Jun 13, 2024Updated last year
- ☆38Jun 10, 2021Updated 4 years ago
- [ICLR'26 Oral] RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments☆38Feb 9, 2026Updated last month
- ☆30Jun 19, 2023Updated 2 years ago
- [NAACL 2022] "SemAttack: Natural Textual Attacks via Different Semantic Spaces" by Boxin Wang, Chejian Xu, Xiangyu Liu, Yu Cheng, Bo Li☆21Jun 11, 2022Updated 3 years ago
- "Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers" (NeurIPS 2019, previously called "A Stratified Approach …☆17Nov 16, 2019Updated 6 years ago
- Inspect: A framework for large language model evaluations☆1,800Updated this week
- ☆134Oct 16, 2025Updated 4 months ago
- Official repo for the paper "Make Some Noise: Reliable and Efficient Single-Step Adversarial Training" (https://arxiv.org/abs/2202.01181)☆25Oct 17, 2022Updated 3 years ago
- Reinforcement Learning Replications is a set of Pytorch implementations of reinforcement learning algorithms.☆25Dec 15, 2024Updated last year
- [NeurIPS2021] Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks☆33Jul 5, 2024Updated last year
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆134Feb 15, 2026Updated 3 weeks ago
- Trained model weights, training and evaluation code from the paper "A simple way to make neural networks robust against diverse image cor…☆62May 24, 2023Updated 2 years ago
- Adversarially Robust Neural Network on MNIST.☆63Feb 4, 2022Updated 4 years ago
- ☆34Jan 25, 2024Updated 2 years ago
- Fine-grained ImageNet annotations☆30May 25, 2020Updated 5 years ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆71Sep 25, 2024Updated last year
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal☆875Aug 16, 2024Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆217Mar 2, 2026Updated last week
- Official implementation for "Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning"☆12Jun 20, 2025Updated 8 months ago