facebookresearch / LWE-benchmarkingLinks
This repository contains code to generate and preprocess Learning with Errors (LWE) data and implementations of four LWE attacks uSVP, SALSA, Cool&Cruel, and Dual Hybrid Meet-in-the-Middle (MitM). We invite contributors to reproduce our results, improve on these methods, and/or suggest new concrete attacks on LWE.
☆54Updated 5 months ago
Alternatives and similar repositories for LWE-benchmarking
Users that are interested in LWE-benchmarking are comparing it to the libraries listed below
Sorting:
- ☆68Updated 10 months ago
- BlindBox is a tool to isolate and deploy applications inside Trusted Execution Environments for privacy-by-design apps☆62Updated last year
- This library supports evaluating disparities in generated image quality, diversity, and consistency between geographic regions.☆20Updated last year
- Pivotal Token Search☆130Updated 3 months ago
- Official Project Page for "Exact Coset Sampling for Quantum Lattice Algorithms" (https://arxiv.org/abs/2509.12341)☆18Updated last week
- ☆26Updated last year
- ☆30Updated 6 months ago
- lossily compress representation vectors using product quantization☆59Updated 6 months ago
- Rust Implementation of micrograd☆53Updated last year
- Public repository containing METR's DVC pipeline for eval data analysis☆124Updated 6 months ago
- Because it's there.☆16Updated last year
- Implementation of SelfExtend from the paper "LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning" from Pytorch and Zeta☆12Updated 11 months ago
- alternative way to calculating self attention☆18Updated last year
- An example implementation of RLHF (or, more accurately, RLAIF) built on MLX and HuggingFace.☆33Updated last year
- Open source platform for the privacy-preserving machine learning lifecycle☆17Updated 2 years ago
- An Automatic Tool to Search for Full Impossible-Differential, Zero-Correlation and Integral Attacks☆11Updated 11 months ago
- Small, simple agent task environments for training and evaluation☆18Updated 11 months ago
- Code for our paper PAPILLON: PrivAcy Preservation from Internet-based and Local Language MOdel ENsembles☆59Updated 5 months ago
- Losslessly encode text natively with arithmetic coding and HuggingFace Transformers☆76Updated last year
- Experimental Code for StructuredRAG: JSON Response Formatting with Large Language Models☆111Updated 6 months ago
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆33Updated 6 months ago
- A collection of lightweight interpretability scripts to understand how LLMs think☆61Updated last week
- BYOeB is a tool to build a chatbot with a custom knowledge base and an expert-in-the-loop.☆33Updated 8 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆58Updated last week
- ☆19Updated last week
- A preprint version of our recent research on the capability of frontier AI systems to do self-replication☆57Updated 10 months ago
- UQ: Assessing Language Models on Unsolved Questions☆27Updated 2 months ago
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆99Updated this week
- An intelligent code optimization system leveraging AI analysis, automated refactoring, and test generation. Built with DSPy and Gradio, i…☆19Updated 8 months ago
- [EMNLP 2024] Tree of Problems: Improving structured problem solving with compositionality☆19Updated 7 months ago