machanic

MMA-Diffusion

[CVPR2024] MMA-Diffusion: MultiModal Attack on Diffusion Models

Awesome-Image-Aesthetic-Assessment

This is a list of resources that utilize machine learning technologies to solve image aesthetic assessment.

SimAesthetics

Taming-Stable-Diffusion-with-Human-Ranking-Feedback

This is the official repo for the paper "Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles", Tang et al. https://arxiv.org/abs/2303.03751

ddom

garak

LLM vulnerability scanner

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

llm-sp

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

OpenLara

Classic Tomb Raider open-source engine

photoguard

Raising the Cost of Malicious AI-Powered Image Editing

quadattack

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.

AnyDoor

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

TABOR

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

backdoor

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

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

Awesome-LM-SSP

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

BruSLiAttack.github.io

QAA

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

olcUTIL_Geometry2D

A Single-Header 2D Geometry Analysis Library

MetaGPT

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

CISA

alphageometry

TrustLLM

[ICML 2024] TrustLLM: Trustworthiness in Large Language Models

viewpoint-robustness

LightZero

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

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

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

DiffMorpher

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

VIAT

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

TransferAttack

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