maxxbw54

maxxbw54's Stars

• OpenBMB/ChatDev

  Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)

  Language:Shell26k3.3k

• amazon-science/recode

  Releasing code for "ReCode: Robustness Evaluation of Code Generation Models"

  Language:Python516

• QData/TextAttack

  TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

  Language:Python3k401

• Yogesh31Hasabe/LeetCode-Experiment-with-AI-Extension

  LeetCode Experiment with AI Extension

  Language:CSS1

• nazmul-me/membership_inference

  Language:Python1

• microsoft/OmniParser

  A simple screen parsing tool towards pure vision based GUI agent

  Language:Jupyter Notebook5.3k415

• bboylyg/BackdoorLLM

  BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks on Large Language Models

  Language:Python886

• llm-attacks/llm-attacks

  Universal and Transferable Attacks on Aligned Language Models

  Language:Python3.5k486

• inspire-group/membership-inference-evaluation

  Systematic Evaluation of Membership Inference Privacy Risks of Machine Learning Models

  Language:Python12518

• microsoft/coderec_programming_states

  Code and Data for: Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming

  Language:Jupyter Notebook319

• iamgroot42/mimir

  Python package for measuring memorization in LLMs.

  Language:Jupyter Notebook13123

• acmsigsoft/submission-checker

  Checks the PDFs submitted to a conference, e.g., for formatting violations and double anonymous violations

  Language:Java613

• penghui-yang/awesome-data-poisoning-and-backdoor-attacks

  A curated list of papers & resources linked to data poisoning, backdoor attacks and defenses against them (no longer maintained)

  20618

• py-why/dowhy

  DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.

  Language:Python7.2k936

• salesforce/causalai

  Salesforce CausalAI Library: A Fast and Scalable framework for Causal Analysis of Time Series and Tabular Data

  Language:Jupyter Notebook26728

• SewoongLab/spectre-defense

  Defending Against Backdoor Attacks Using Robust Covariance Estimation

  Language:Python205

• goutham7r/backdoors-for-code

  Language:Python64

• SCLBD/BackdoorBench

  Language:Jupyter Notebook43271

• yuezunli/ISSBA

  Invisible Backdoor Attack with Sample-Specific Triggers

  Language:Python9317

• salesforce/CodeTF

  CodeTF: One-stop Transformer Library for State-of-the-art Code LLM

  Language:Python1.5k102

• ALFA-group/adversarial-code-generation

  [ICLR 2021] "Generating Adversarial Computer Programs using Optimized Obfuscations" by Shashank Srikant, Sijia Liu, Tamara Mitrovska, Shiyu Chang, Quanfu Fan, Gaoyuan Zhang, and Una-May O'Reilly

  Language:Python275

• bigcode-project/bigcode-evaluation-harness

  A framework for the evaluation of autoregressive code generation language models.

  Language:Python852223

• evalplus/evalplus

  Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024

  Language:Python1.3k114

• google-deepmind/codesembench

  Language:Python151

• NWPU-IST/sbrbench

  Language:Python144

• centerforaisafety/Intro_to_ML_Safety

  6519

• SEEDGuard/SEVAL

  Auto-evaluation for SE tasks.

  Language:Python413

• NAIST-SE/DevGPT

  This is Research Artifact for DevGPT Dataset

  3819

• Lyz1213/Backdoored_PPLM

  Language:C#141

• THUYimingLi/backdoor-learning-resources

  A list of backdoor learning resources

  1.1k168