osint_toolkit

OSINT Toolkit Warning OSINT Toolkit is not production ready yet. This is an early prototype, that still needs some work to be done. A fullstack web application built for security analysts OSINT Toolkit is a self-hostable, on-demand analysis platform designed for security specialists. It...

Stevos-AI-Blocklist

Stevo's AI Blocklist A filter list for uBlock Origin and AdGuard that hides specific website features which use Generative AI and content labeled as AI-generated. Available for PC/Linux Firefox, Chrome, Edge, Brave, macOS Firefox, Chrome, Edge, Safari, Android Firefox, and iOS/iPadOS Safari, Brav...

offensive-ai-compilation

Offensive AI Compilation Una lista curata di risorse utili che coprono l'Offensive AI. 📁 Contenuti 📁 🚫 Abuse 🚫 🧠 Adversarial Machine Learning 🧠 ⚡ Attacchi ⚡ 🔒 Estrazione 🔒 ⚠️ Limitazioni ⚠️ 🛡️ Azioni difensive 🛡️ 🔗 Link utili 🔗 ⬅️ Inversione o inferenza ⬅️ 🛡️ Azioni difensive 🛡️ 🔗 Link utili 🔗 💉...

PyRIT

Strumento Python di identificazione dei rischi per l'IA generativa PyRIT Lo strumento Python di identificazione dei rischi per l'IA generativa PyRIT è un framework open source progettato per consentire a professionisti della sicurezza e a ingegneri di identificare in modo proattivo i rischi nei...

PurpleLlama

🤗 Modelli su Hugging Face | Blog | Sito web | Paper CyberSec Eval | Paper Llama Guard Purple Llama Purple Llama è un progetto-ombrello che nel tempo riunirà strumenti e valutazioni per aiutare la comunità a sviluppare in modo responsabile con modelli di IA generativa aperti. La versione iniziale...

AI-Red-Teaming-Playground-Labs

Laboratori Playground di AI Red Teaming Questo repository contiene le sfide per i laboratori utilizzati nel corso "AI Red Teaming in Practice". Il corso è stato originariamente tenuto al Black Hat USA 2024 da Dr. Amanda Minnich e Gary Lopez. Martin Pouliot si è occupato dell'infrastruttura e del...

PyRIT

Python Risk Identification Tool for generative AI PyRIT The Python Risk Identification Tool for generative AI PyRIT is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems. !WARNING PyRIT has moved! Please see...

bouncy-castle-generative-test-poc

Generative testing bouncy castle vulnerability CVE-2020-28052 Running the tests Test the vulnerable versions defaults to 1.66 $ clojure -M:test $ clojure -M:test:v1.65 Test the versions before the vuln and after the patch 1.67 $ clojure -M:test:v1.64 $ clojure -M:test:patched Links...

Adversarial Debiasing of Machine Learning Models for Enhanced Network Security against DDoS Attacks

Distributed Denial of Service attacks are a growing threat to network infrastructure, and new techniques, including the use of generative AI, make them harder to detect. Traditional detection systems, such as rule based firewalls, often fail to identify these evolving attack patterns. In this...

JEV As a Judge for Agent Trace Security: An Empirical Comparison with Generative LLM Judges

Security evaluation of tool-using agents requires judging actions in context, yet generative judges add latency, explanation overhead, and output-validation failures. We study whether JEV, a typed decision model, offers a useful alternative for retrospective trace classification. We evaluate JEV...

The SOC Doesn't Need to Start Over with Every Alert

Security leaders keep debating whether AI will produce an entirely new class of cyberattack. The nearer change is quieter and already visible: AI has made a failed attack cheap to retry. The routine version looks like this. An attacker lands on a low-privilege cloud account, and the first try at...

Kibana 9.4.7, 9.5.0 Security Update (ESA-2026-85)

Unintended Proxy or Intermediary 'Confused Deputy' in Kibana Leading to Privilege Escalation Unintended Proxy or Intermediary 'Confused Deputy' CWE-441 in Kibana Agent Builder can lead to privilege escalation. A non-administrative user able to edit a shared agent could cause privileged operations...

Trusted Model Environment for Private Semantic Computations

A private semantic computation primitive enables parties to privately compute over structured and unstructured data that requires understanding its semantics, context, and relationships. Standard cryptographic primitives e.g., multiparty computation do not readily support such computation...

SAGEGAN: Style-Based Anomaly Detection with Gaussian Embeddings Using Generative Adversarial Networks

Malware evolves faster than rule-based and signature-driven detection pipelines. This paper presents SAGEGAN, a benign-only trained malware anomaly detection framework that converts portable executable files into compact three-channel images and models benign structure through style-conditioned...

RatHat Android Malware Uses AI to Target Banking Credentials in Real Time

RatHat Android malware uses generative AI to navigate infected devices, steal banking credentials, intercept OTP codes and reinstall itself after removal again...

Unlocking Cross-Scenario Physical Layer Security: A Mixture-Of-Experts Framework with Generative Diffusion Models

The future 6G networks are expected to incorporate a proliferation of wireless services in diverse environments, which presents a significant challenge for information security. Conventionally optimization always requires recalculation and learning strategy often suffers poor generalization, whic...

EUVD-2026-77131

A vulnerability was determined in Anil-matcha Open-Generative-AI up to 1.0.11/2.0.0. Affected by this vulnerability is the function renderHistory of the file ImageStudio.js of the component Studio Components. This manipulation causes cross site scripting. The attack may be initiated remotely. The...

EUVD-2026-77138

A vulnerability was identified in Anil-matcha Open-Generative-AI up to 1.0.11/2.0.0. Affected by this issue is some unknown functionality of the file /api/upload-binary of the component S3 Upload. Such manipulation of the argument x-proxy-target-url leads to unrestricted upload. The attack may be...

CVE-2026-90602

A vulnerability was determined in Anil-matcha Open-Generative-AI up to 1.0.11/2.0.0. Affected by this vulnerability is the function renderHistory of the file ImageStudio.js of the component Studio Components. This manipulation causes cross site scripting. The attack may be initiated remotely. The...

CVE-2026-90603

A vulnerability was identified in Anil-matcha Open-Generative-AI up to 1.0.11/2.0.0. Affected by this issue is some unknown functionality of the file /api/upload-binary of the component S3 Upload. Such manipulation of the argument x-proxy-target-url leads to unrestricted upload. The attack may be...