alibi-detect

Alibi Detect is a source-available Python library focused on outlier , adversarial and drift detection. The package aims to cover both online and offline detectors for tabular data, text, images and time series. Both TensorFlow and PyTorch backends are supported for drift detection. Documentation...

In0ri

In0ri es un sistema automatizado impulsado por IA para la detección de defacement en sitios web. Introducción In0ri actúa como un vigilante inteligente para tus aplicaciones web. En lugar de depender de la monitorización tradicional del código fuente, simula el comportamiento de un usuario real...

deep-pwning

Deep-pwning is a lightweight framework for experimenting with machine learning models with the goal of evaluating their robustness against a motivated adversary. Note that deep-pwning in its current state is no where close to maturity or completion. It is meant to be experimented with, expanded...

Ruse

Ruse Aplicación móvil basada en la cámara que intenta modificar fotos para preservar su utilidad para los humanos, al mismo tiempo que las vuelve inutilizables para sistemas de reconocimiento facial. Instalación 1 Método sencillo: esperar y descargar la aplicación desde la tienda de aplicaciones...

ExploitTensorflowCVE-2021-37678

CVE-2021-37678 Exploit To exploit the vulnerability, it is necessary to start a Docker container with an environment prepared to run Tensorflow with version 2.2.3 which still has the vulnerability. It consists of: An AMD 64-bit architecture, CPU or GPU that can execute AVX instructions Python...

CVE-2024-3660-PoC

CVE-2024-3660 – TensorFlow Keras Arbitrary Code Execution via Malicious Model Overview CVE-2024-3660 is an arbitrary code execution vulnerability in TensorFlow's Keras framework affecting versions 2.13. It allows an attacker to embed Python code inside a model e.g., via a Lambda layer which...

eyeballer

Eyeballer Give those screenshots of yours a quick eyeballing. Eyeballer is meant for large-scope network penetration tests where you need to find "interesting" targets from a huge set of web-based hosts. Go ahead and use your favorite screenshotting tool like normal EyeWitness or GoWitness and th...

AI_HACKING

AIHACKING Collection of CVEwork on tenserflow binary pwning it FOR CVE202223591WHICH IS STILL UNDER WORK I NEED TO FIGURE OUT HOW TO TURN BACK JSON TO PROTOBUF AND THAN DO with tf.io.gfile.GFile'test.pb', 'rb' as f: graphdef = tf.compat.v1.GraphDef print"aiciaaaaaaaaaaaaaa" printgraphdef...

frigate

Frigate NVR™ - 一个具有实时目标检测的本地 NVR English | 简体中文 一个完整的本地网络视频录像机（NVR），专为Home Assistant设计，具备 AI 目标/物体检测功能。使用 OpenCV 和 TensorFlow 在本地为 IP 摄像头执行实时物体检测。 强烈推荐使用 GPU 或者 AI 加速器（例如Google Coral 加速器 或者 Hailo等）。它们的运行效率远远高于现在的顶级 CPU，并且功耗也极低。 通过自定义组件与 Home Assistant 紧密集成 设计上通过仅在必要时和必要地点寻找目标，最大限度地减少资源使用并最大化性能...

deep-pwning

Deep-pwning 是一个轻量级的框架，用于对机器学习模型进行实验，目标是评估它们在面对有动机的对手时的鲁棒性。 请注意，当前状态的 deep-pwning 远未 达到成熟或完成。它旨在供您实验、扩展和延伸。只有这样，我们才能真正帮助它成为 统计机器学习模型的渗透测试工具包 。 背景 研究人员发现，让机器学习模型（分类器、聚类器、回归器等）做出客观上错误的决策是出乎意料地容易。这一研究领域被称为...

DeepPass

DeepPass Dockerized application that analyzes documents for password candidates. The blogpost "DeepPass — Finding Passwords With Deep Learning" gives more detail on the approach and development of the model. To run: docker-compose up This will expose http://localhost:5000 where documents can be...

cleverhans

CleverHans（最新版本：v4.0.0） 本仓库包含 CleverHans 的源代码，这是一个用于评估机器学习系统对 对抗样本 漏洞的 Python 库。 你可以在随附的 博客 上了解更多关于此类漏洞的信息。 CleverHans 库持续开发中，始终欢迎 贡献 最新的攻击和防御方法。 特别是，我们始终欢迎帮助解决当前 开放的问题。 自 v4.0.0 起，CleverHans 支持 3 种框架：JAX、PyTorch 和 TF2。我们目前优先在 PyTorch 中实现攻击， 但非常欢迎为所有 3 种框架做出贡献。在 v3.1.0 及更早版本中， CleverHans 支持...

CLEANSTART-2026-SI19530 Security fix for CVE-2026-44899 applied in: tensorflow-gpu-jupyter 2.21.0-r5

Security vulnerability affects the tensorflow-gpu-jupyter package. This issue is resolved in later releases. See references for vulnerability details...

CLEANSTART-2026-DO33300 Security fix for CVE-2026-44897 applied in: tensorflow-gpu-jupyter 2.21.0-r5

Security vulnerability affects the tensorflow-gpu-jupyter package. This issue is resolved in later releases. See references for vulnerability details...

CLEANSTART-2026-PO47077 Security fix for CVE-2026-44898 applied in: tensorflow-gpu-jupyter 2.21.0-r5

Security vulnerability affects the tensorflow-gpu-jupyter package. This issue is resolved in later releases. See references for vulnerability details...

CLEANSTART-2026-CB04703 Security fix for CVE-2026-42557 applied in: tensorflow-gpu-jupyter 2.21.0-r5

Security vulnerability affects the tensorflow-gpu-jupyter package. This issue is resolved in later releases. See references for vulnerability details...

CLEANSTART-2026-RE32707 Security fix for CVE-2026-33079 applied in: tensorflow-gpu-jupyter 2.21.0-r5

Security vulnerability affects the tensorflow-gpu-jupyter package. This issue is resolved in later releases. See references for vulnerability details...

CLEANSTART-2026-KE39444 Security fix for CVE-2026-42266 applied in: tensorflow-gpu-jupyter 2.21.0-r5

Security vulnerability affects the tensorflow-gpu-jupyter package. This issue is resolved in later releases. See references for vulnerability details...

CLEANSTART-2026-OX78672 Security fix for CVE-2026-40171 applied in: tensorflow-gpu-jupyter 2.21.0-r5

Security vulnerability affects the tensorflow-gpu-jupyter package. This issue is resolved in later releases. See references for vulnerability details...

CLEANSTART-2026-JD56309 Security fix for CVE-2025-61669 applied in: tensorflow-gpu-jupyter 2.21.0-r5

Security vulnerability affects the tensorflow-gpu-jupyter package. This issue is resolved in later releases. See references for vulnerability details...