10 个仓库
Awesome GitHub RepositoriesAdversarial Attacks
Tools for testing model robustness and creating adversarial perturbations.
Explore 10 awesome GitHub repositories matching part of an awesome list · Adversarial Attacks. Refine with filters or upvote what's useful.
Awesome Adversarial Attacks GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- cs231n/cs231n.github.io
cs231n/cs231n.github.io
10,923在 GitHub 上查看This project is a static educational website and comprehensive curriculum focused on computer vision and deep learning. It serves as a public repository of instructional materials, lecture notes, and technical guides specifically detailing convolutional neural networks and visual recognition. The site is developed using static-site generation to host course documentation and student project directories. It provides structured academic resources that guide learners through image classification, generative modeling, and the implementation of various neural network architectures. The curriculum
Teaches how to generate adversarial examples using gradient-based methods to test model robustness.
Jupyter Notebook - opencv/opencv_contrib
opencv/opencv_contrib
10,116在 GitHub 上查看This project is a collection of optional, community-contributed algorithms and specialized vision tools that extend the core OpenCV framework. It serves as a comprehensive library of extra modules for computer vision research, providing advanced toolsets for image processing, visual data analysis, and object detection. The library includes specialized frameworks for augmented reality tracking, biometric face recognition, and three-dimensional pose estimation. It provides distinct capabilities for identifying AR markers, tracking 3D object silhouettes, and performing neural network vulnerabili
Provides tools for generating synthetic noise patterns to test the robustness of neural networks against misclassification attacks.
C++opencv - homanp/superagent
homanp/superagent
6,631在 GitHub 上查看Superagent is a framework for AI assistant orchestration and agent security. It provides the tools to build intelligent assistants that integrate external APIs and maintain conversation memory to automate complex tasks. The project focuses on AI agent security through adversarial testing, red teaming, and the detection of prompt injections and malicious tool calls. It includes automated vulnerability patching, which scans codebases and configurations for security flaws and generates pull requests with fixes. The platform supports retrieval augmented generation by connecting language models t
Simulates targeted attack scenarios against deployed agents to discover security vulnerabilities and exploit paths.
TypeScript - cleverhans-lab/cleverhans
cleverhans-lab/cleverhans
6,443在 GitHub 上查看Cleverhans is an adversarial machine learning library and toolkit designed to generate adversarial examples, incorporate them into training loops, and benchmark the resilience of machine learning models. It provides a gradient-based attack framework for constructing both white-box and black-box attacks to identify model misclassifications. The project includes capabilities for model robustness benchmarking, allowing users to evaluate and verify how models resist evasion attacks and malicious input perturbations. It also facilitates adversarial training to increase a model's resistance to pert
Implements black-box adversarial attacks by using substitute imitators to identify model misclassifications.
Jupyter Notebookbenchmarkingmachine-learningsecurity - trusted-ai/adversarial-robustness-toolbox
Trusted-AI/adversarial-robustness-toolbox
6,056在 GitHub 上查看The Adversarial Robustness Toolbox (ART) is an open-source library that provides a unified framework for evaluating, defending, and certifying machine learning models against adversarial threats. It wraps models from any framework behind a common estimator interface, enabling composable pipelines for attack generation, defense application, robustness certification, and privacy auditing across evasion, poisoning, and extraction threats. The library distinguishes itself by covering the full adversarial ML security lifecycle within a single toolkit. It supports gradient-based adversarial example
Provides a framework for generating evasion, poisoning, and extraction attacks to stress-test model robustness.
Pythonadversarial-attacksadversarial-examplesadversarial-machine-learning - llm-attacks/llm-attacks
llm-attacks/llm-attacks
4,509在 GitHub 上查看This repository provides tools and methodologies for studying adversarial attacks on large language models. It focuses on understanding how carefully crafted inputs can manipulate or bypass the safety mechanisms of LLMs, enabling researchers to probe model vulnerabilities and improve their robustness. The project covers techniques for generating adversarial prompts, evaluating model responses under attack conditions, and analyzing the effectiveness of different attack strategies.
Provides a comprehensive toolkit for generating gradient-based adversarial prompts to evaluate model robustness.
Python - vdigpku/cmua-watermark
VDIGPKU/CMUA-Watermark
110在 GitHub 上查看The official code for CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes (AAAI2022) arxiv. It is based on disrupting-deepfakes .
Cross-model universal adversarial watermarks for combating deepfakes.
Python - jwliang007/pff
JWLiang007/PFF
This repository contains the official PyTorch implementation of the following paper at ICLR 2024 (Spotlight):
Backdoor attacks targeting face forgery detection models.
Python - ningyu1991/scalableganfingerprints
ningyu1991/ScalableGANFingerprints
Ning Yu\, Vladislav Skripniuk\, Dingfan Chen, Larry Davis, Mario Fritz *Equal contribution ICLR 2022 Spotlight
Scalable fingerprinting for responsible generative model disclosure.
- abstractteen/antiforgery
AbstractTeen/AntiForgery
An example of Anti-Forgery: Towards a Stealthy and Robust DeepFake Disruption Attack via Adversarial Perceptual-aware Perturbations (to be presented at the IJCAI-ECAI 2022). This repository contains code for crafting perceptual-aware perturbation in the Lab color space to attack an…
Stealthy deepfake disruption via adversarial perceptual perturbations.
