1 个仓库
Awesome GitHub RepositoriesEvasion Attack Generators
Runs one or more evasion attacks against a classification model, optimizing attack strength by targeting only correctly classified samples.
Distinct from Evasive Payload Generators: Distinct from Evasive Payload Generators: focuses on generating adversarial inputs for ML models, not payloads for endpoint protection bypass.
Explore 1 awesome GitHub repository matching security & cryptography · Evasion Attack Generators. Refine with filters or upvote what's useful.
Awesome Evasion Attack Generators 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。
- 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
Generates evasion attacks against classification models, optimizing strength on correctly classified samples.
Pythonadversarial-attacksadversarial-examplesadversarial-machine-learning
