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...

CVE-2022-32898

CVE-2022-32898: ANEProgramCreate multiple kernel memory corruption Nov 23, 2022 • Mohamed GHANNAM @simo36 저자 commnet I'm sharing two other iOS kernel vulnerabilities reachable from the default app sandbox that don’t require you to open a UserClient: +16 kernel bugs I reported to Apple have been...

Kaonashi

Kaonashi Project: RootedCON 2019 This repository contains several directories: Sorted Masks for hashcat Advanced Rules for hashcat Links to download the Kaonishi's Wordlists Slides used in our talk I know your p4$$w0rd and if I don't, I will guess it... at RootedCON 2019 A clone may not be...

recipe-blog-encoding

recipe-blog-encoding !WARNING This project is entirely vibe-coded likely partially plagiarized from this repository and the author is a dumb-dumb who just thought the idea was funny Use SEO-gaming recipe preambles as a vehicle for encoding secret messages the prompt can really be anything though,...

Intel Neural Compressor <2.5.0 - SQL Injection

Improper input validation in some IntelR Neural Compressor software before version 2.5.0 may allow an unauthenticated user to potentially enable escalation of privilege via remote access. id: CVE-2024-22476 info: name: Intel Neural Compressor 2.5.0 - SQL Injection author: ritikchaddha,daffainfo...

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...

challenge_repo

🎲 The Entropy Challenge 🇬🇧 Read in English | 🇹🇷 Türkçe Oku Introduction We have developed a next-generation random number generator that processes Radio Frequency RF Noise through a proprietary Neural Network architecture , followed by SHA-3 post-processing. We claim this source provides True...

backdoor-learning-resources

Recursos de Backdoor Learning Este repositorio de Github resume una lista de recursos de Backdoor Learning. Para más detalles y los criterios de categorización, consulte nuestro estudio. Haremos todo lo posible por mantener continuamente este repositorio de Github de forma mensual. ¿Por qué...

robustness

Paquete robustness Instalación mediante pip: pip install robustness Lee la documentación: https://robustness.readthedocs.io/en/latest/index.html robustness es un paquete que creamos estudiantes del MadryLab para que entrenar, evaluar y explorar redes neuronales sea flexible y sencillo. Lo usamos ...

certified-unlearning-neural-networks-icml-2025

Desaprendizaje certificado para redes neuronales Este repositorio contiene la implementación del artículo "Certified Unlearning for Neural Networks" ICML 2025. Métodos PABI Amplificación de privacidad por iteración : Gradient Clipping en el artículo DP-SGD : Con privacidad de grupo como se descri...

weightBufs

WeightBufs: WeightBufs ist ein Kernel-Lese-/Schreib-Exploit für alle Apple-Geräte mit Neural-Engine-Unterstützung. Bugs und Exploit von @simo36, weitere Details zu den Schwachstellen und den Ausnutzungstechniken findest du in meinen Präsentationsfolien bei POC. Der Exploit verlässt sich nicht auf...

AntiVE-BehaviorWatch

AntiVE-BehaviorWatch Verifica del comportamento umano basata su AI integrata per la ricerca in cybersecurity. Cos'è AntiVE-BehaviorWatch? AntiVE-BehaviorWatch è un progetto di ricerca sulla cybersecurity basato su Windows che esplora un nuovo approccio al controllo dell'esecuzione utilizzando...

Insider-Threat

Modelli a grafi per la minaccia interna R5.2 & R6.2 Questa repository contiene la preparazione dei dati, l'estrazione delle feature e modelli basati su grafi GCN-NN, GCN-BiLSTM e GCN-BiLSTM+Attention per segnali impliciti+espliciti per il rilevamento delle minacce interne utilizzando il CMU CERT...

nCPU

Ein vollständiger Computer, bei dem jede Schicht – Arithmetik, Betriebssystem, Compiler, Display – entweder ein trainiertes neuronales Netz ist oder vollständig auf der GPU läuft. Das Modell läuft nicht auf dem Computer. Das Modell ist der Computer. nCPU ist ein Repository, das eine These aus fün...

CVE-2026-20906

Protection mechanism failure for some IntelR Neural Compressor software before version v3.6 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege. This...

CVE-2026-20913

Improper input validation for some IntelR Neural Compressor software before version v3.7 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with an authenticated user combined with a low complexity attack may enable escalation of privilege. This...

CVE-2026-20913

Improper input validation for some IntelR Neural Compressor software before version v3.7 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with an authenticated user combined with a low complexity attack may enable escalation of privilege. This...

CVE-2026-20913

Improper input validation for some IntelR Neural Compressor software before version v3.7 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with an authenticated user combined with a low complexity attack may enable escalation of privilege. This...

CVE-2026-20913

CVE-2026-20913 describes an issue in some Intel Neural Compressor software prior to v3.7 where improper input validation in Ring 3: User Applications may allow a local privilege escalation. An unprivileged attacker with an authenticated user and low complexity could achieve escalation with no use...

EUVD-2026-56513

Improper input validation for some IntelR Neural Compressor software before version v3.7 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with an authenticated user combined with a low complexity attack may enable escalation of privilege. This...