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...

frigate

Frigate NVR™ - Detección de objetos en tiempo real para cámaras IP English | 简体中文 Un NVR completo y local diseñado para Home Assistant con detección de objetos mediante IA. Utiliza OpenCV y Tensorflow para realizar la detección de objetos en tiempo real localmente para cámaras IP. Se recomienda...

Ruse

Ruse Mobile camera-based application that attempts to alter photos to preserve their utility to humans while making them unusable for facial recognition systems. Installation 1 Easy Method: Wait and download app from appropriate app store. 2 Download and run ios app via XCode see Development setu...

alibi-detect

Alibi Detect es una biblioteca de Python de código disponible centrada en la detección de outliers , adversarial y deriva. El paquete tiene como objetivo cubrir detectores tanto en línea como fuera de línea para datos tabulares, texto, imágenes y series temporales. Tanto los backends de TensorFlo...

AI_HACKING

AIHACKING Colección de CVEtrabajo sobre explotación binaria de tenserflow PARA CVE202223591QUE SIGUE EN DESARROLLO NECESITO AVERIGUAR CÓMO CONVERTIR JSON DE VUELTA A PROTOBUF Y LUEGO HACER with tf.io.gfile.GFile'test.pb', 'rb' as f: graphdef = tf.compat.v1.GraphDef print"aiciaaaaaaaaaaaaaa"...

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...

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...

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...

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...

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 última versión: v4.0.0 Este repositorio contiene el código fuente de CleverHans, una biblioteca de Python para evaluar la vulnerabilidad de los sistemas de aprendizaje automático a los ejemplos adversariales. Puedes aprender más sobre estas vulnerabilidades en el blog adjunto. La...

In0ri

In0ri è un sistema automatizzato di rilevamento di defacement di siti web basato su intelligenza artificiale. Introduzione In0ri funge da watchdog intelligente per le tue applicazioni web. Invece di basarsi sul monitoraggio tradizionale del codice sorgente, simula il comportamento di un utente...

AZL-98217 CVE-2026-15310 affecting package tensorflow 2.16.1-11

When decompressing crafted zip files using the bzip/LZMA/Zstandard compressions, Python could use an attacker-controlled size to pre-allocate memory, possibly resulting in memory exhaustion...

CVE-2026-73417 vulnerabilities

Vulnerabilities for packages: tensorflow-cpu-jupyter...

CVE-2026-73415 vulnerabilities

Vulnerabilities for packages: tensorflow-cpu-jupyter...

CVE-2026-73416 vulnerabilities

Vulnerabilities for packages: tensorflow-cpu-jupyter...

CVE-2026-20728

Protection mechanism failure for some Intel Extension for TensorFlow software before version 2.15.0.3 within Ring 3: User Applications may allow an escalation of privilege. System software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege...

CVE-2026-20728

Protection mechanism failure for some Intel Extension for TensorFlow software before version 2.15.0.3 within Ring 3: User Applications may allow an escalation of privilege. System software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege...

EUVD-2026-56478

Protection mechanism failure for some Intel Extension for TensorFlow software before version 2.15.0.3 within Ring 3: User Applications may allow an escalation of privilege. System software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege...

CVE-2026-20728

Intel Extension for TensorFlow software kidded with Protection mechanism failure before version 2.15.0.3, located in Ring 3: User Applications. This vulnerability could allow a local-privileged attacker with high privileges and low complexity, in combination with passive user interaction, to esca...