
SANS_THIR16
SANS Hunting on the Cheap

SANS Hunting on the Cheap

The ultimate steganography and digital forensics toolkit. Hide and extract data across images, audio, video, documents, and network packets, or run…

The world's fastest agentic crawler. Reclaimed. Reinvented. Ready for war.

Step-by-step tutorial on using Google's Gemma 4 E4B local AI model to reverse engineer a Windows crackme with Ghidra, including setup for local…

Research pipeline for detecting latent indirect prompt-injection exposure signals in agentic LLMs via hidden-state probing, including trace…

[CVPR 2025-ADVML] Official Repository for `Attacking Attention of Foundation Models Effectively Disrupts Downstream Tasks`

Reverse Shell Detection with Machine Learning

Restructured and Collaborated SIEM and CVSS Infrastructure. Presented at Blackhat Asia Arsenal 2020.

AI-curated blocklist of 3,000,000+ domains for blocking ads, trackers, malware, and cryptojacking. Integrates with hosts files, Pi-hole, and browser…

YC (S26) | Open Computer History | Record your screen continuously locally and provide context to your agents (Claude, Codex, Openclaw, Hermes,…

Interpretability and explainability of data and machine learning models


Automated behavioral evaluation framework for LLMs that generates diverse test scenarios to probe for sycophancy, bias, and other safety-relevant…

LSTM-based classifier for detecting domain generation algorithm (DGA) domains, with Keras implementations of neural network and bigram models for DNS…

Android Antivirus which doesn't require root, adb, ca install and cloud with many features and ways to detect more zero-day malware

Framework for auditing machine learning algorithms against adversarial attacks and biases, providing educational tools and an academic paper to…

Curated reading list and taxonomy of attack and defense research for mobile on-device AI systems, covering adversarial, backdoor, model stealing, and…

Evaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in normal-looking text, with…