REsampling Uncertainty Bounds for Evaluating NLP

alpha-beta-CROWN: An Efficient, Scalable and GPU Accelerated Neural Network Verifier (winner of VNN-COMP 2021, 2022, 2023, 2024, 2025)

An Open-Source Package for Textual Adversarial Attack.

AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM

Research into chain-of-thought monitoring as an AI Control protocol

[ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models".

The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.

An extension of nanoGCG which allows multi-prompt, dual model optimization

Code for the paper "Defeating Prompt Injections by Design"

Provider-agnostic, open-source evaluation infrastructure for language models

[arXiv 2025] Pre-training script for Clinical ModernBERT

A framework for few-shot evaluation of language models.

Auto get diffusion nlp papers in Axriv. More papers Information can be found in another repository "Diffusion-LM-Papers".

A curated list of papers related to constrained decoding of LLM, along with their relevant code and resources.

Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.

A curation of awesome tools, documents and projects about LLM Security.

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

Solve puzzles. Improve your pytorch.

interactive heightmaps from terrain data

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends