machanic

MetaGPT

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

OpenLara

Classic Tomb Raider open-source engine

alphageometry

kernl

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

LightZero

[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)

Safety-Prompts

Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts，用于评估和提升大模型的安全性。

Awesome-LM-SSP

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

photoguard

Raising the Cost of Malicious AI-Powered Image Editing

torchopt

TorchOpt is an efficient library for differentiable optimization built upon PyTorch.

TrustLLM

[ICML 2024] TrustLLM: Trustworthiness in Large Language Models

DiffMorpher

Official Code for DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing (CVPR 2024)

llm-sp

Papers and resources related to the security and privacy of LLMs 🤖

olcUTIL_Geometry2D

A Single-Header 2D Geometry Analysis Library

backdoor

Code implementation of the paper "Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks", at IEEE Security and Privacy 2019.

SN-Net

[CVPR 2023 Highlight] This is the official implementation of "Stitchable Neural Networks".

TransferAttack

TransferAttack is a pytorch framework to boost the adversarial transferability for image classification.

Visual-Adversarial-Examples-Jailbreak-Large-Language-Models

Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models

clip_text_span

official implementation of "Interpreting CLIP's Image Representation via Text-Based Decomposition"

viewpoint-robustness

AnyDoor

AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models

DeepZero

[ICLR'24] "DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training" by Aochuan Chen*, Yimeng Zhang*, Jinghan Jia, James Diffenderfer, Jiancheng Liu, Konstantinos Parasyris, Yihua Zhang, Zheng Zhang, Bhavya Kailkhura, Sijia Liu

fmixup

Decision-based Adversarial Attack with Frequency Mixup

TABOR

Implementation of TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems (https://arxiv.org/pdf/1908.01763.pdf)

NeRFool

[ICML 2023] "NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations" by Yonggan Fu, Ye Yuan, Souvik Kundu, Shang Wu, Shunyao Zhang, Yingyan (Celine) Lin

CISA

QAA

This is the official code repository for paper "Quantization Aware Attack: Enhancing Transferable Adversarial Attacks by Model Quantization"

VIAT

Official implementation of VIAT (Viewpoint-Invariant Adversarial Training) and GMVFool

BruSLiAttack.github.io

quadattack