thestephencasper / benchmarking_interpretability
☆34Updated last year
Alternatives and similar repositories for benchmarking_interpretability:
Users that are interested in benchmarking_interpretability are comparing it to the libraries listed below
- ☆14Updated last year
- Privacy backdoors☆51Updated 11 months ago
- ☆21Updated 9 months ago
- ☆35Updated 6 months ago
- Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Works…☆14Updated 10 months ago
- ☆54Updated 2 years ago
- Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]☆43Updated 11 months ago
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆111Updated 10 months ago
- ☆20Updated 3 months ago
- Starter kit and data loading code for the Trojan Detection Challenge NeurIPS 2022 competition☆33Updated last year
- ☆16Updated last year
- Code for the paper "The Journey, Not the Destination: How Data Guides Diffusion Models"☆22Updated last year
- Code for the paper "Evading Black-box Classifiers Without Breaking Eggs" [SaTML 2024]☆20Updated last year
- ☆42Updated 2 years ago
- Independent robustness evaluation of Improving Alignment and Robustness with Short Circuiting☆16Updated last week
- ☆31Updated last year
- Codebase for Obfuscated Activations Bypass LLM Latent-Space Defenses☆16Updated 2 months ago
- ☆68Updated last year
- ☆41Updated last year
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated last year
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet☆30Updated last year
- Code for the paper "A Light Recipe to Train Robust Vision Transformers" [SaTML 2023]☆52Updated 2 years ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆100Updated last year
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆62Updated last year
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆68Updated last year
- ModelDiff: A Framework for Comparing Learning Algorithms☆56Updated last year
- Data for "Datamodels: Predicting Predictions with Training Data"☆97Updated last year
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆86Updated 11 months ago
- What do we learn from inverting CLIP models?☆54Updated last year
- Recycling diverse models☆44Updated 2 years ago