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

Compress your input to ChatGPT or other LLMs, to let them process 2x more content and save 40% memory and GPU time.

Home of CodeT5: Open Code LLMs for Code Understanding and Generation

Proof of concept code for poisoning code generation models.

A repository of trojaned neural models of code along with a poisoning framework for trojaning such models.

Train transformer language models with reinforcement learning.

Evaluating and Enhancing the Robustness of Code Pre-trained Models through Structure-Aware Adversarial Samples Generation, EMNLP 2023

Can large language models provide useful feedback on research papers? A large-scale empirical analysis.

OpenMMLab Self-Supervised Learning Toolbox and Benchmark

Code for the AAAI 2023 paper "CodeAttack: Code-based Adversarial Attacks for Pre-Trained Programming Language Models

An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)

Enhacing Code Pre-trained Models by Contrastive Learning

发在B站上的视频对应的源代码，有些内容不是原创的会在代码中注释。

Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"