


A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

Interpretability and explainability of data and machine learning models

Proof-of-concept demos and research on indirect prompt injection attacks against application-integrated LLMs, covering data exfiltration, remote…

The AI Security Verification Standard (AISVS) focuses on providing developers, architects, and security professionals with a structured checklist to…

Algorithms for outlier, adversarial and drift detection

Clusters and elements to attach to MISP events or attributes (like threat actors)

An information security preparedness tool to do adversarial simulation.

Curated list of backdoor learning papers, surveys, and toolboxes, organizing poisoning-based attacks and defenses in deep learning for researchers…

Loading Remote AES Encrypted PE in memory , Decrypted it and run it

The exploit server for out-of-band findings. Point a target at a domain you own. Every HTTP request and every email it sends back lands in a…

PoCs and tools for investigation of Windows process execution techniques

Bluetooth keystroke injection exploit PoCs for CVE-2023-45866, CVE-2024-21306, and CVE-2024-0230 targeting Android, Linux, macOS, and iOS via…

A security scanner for your LLM agentic workflows

Metasploit for machine learning.

Threadless Process Injection using remote function hooking.

Protection against Model Serialization Attacks

An advanced in-memory evasion technique fluctuating shellcode's memory protection between RW/NoAccess & RX and then encrypting/decrypting its contents