
better_opts_attacks
Attack framework for breaking fine-tuning based prompt injection defenses (SecAlign, SecAlign++, StruQ) using architecture-aware adversarial attacks…

Attack framework for breaking fine-tuning based prompt injection defenses (SecAlign, SecAlign++, StruQ) using architecture-aware adversarial attacks…

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

Adversary-resilient deep learning architecture for secure 5G indoor localization, combining CNN and multi-head attention to defend against signal…

Lightweight framework for evaluating machine learning model robustness against adversarial attacks. Generates adversarial samples to test…

Detect EDR's exceptions by inspecting processes' loaded modules

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and…

Modular LLM vulnerability scanner that probes for hallucination, data leakage, prompt injection, jailbreaks, and toxicity using static, dynamic, and…

Encrypted C2 and post-exploitation framework for red teams, with modular PowerShell/Python/C#/Go agents, many offensive modules, and easy…

Adversary simulation and Red teaming platform with AI

Python library for adversarial machine learning security, enabling red and blue teams to run evasion, poisoning, extraction, and inference attacks…

Collection of machine learning tools for security: automated penetration testing, adversarial example generation, web vulnerability scanning, and…

Realistic APT adversary simulation campaigns with custom C2 frameworks, backdoors, stagers, and bootloaders mirroring state-sponsored TTPs for red…

Real-time deepfake toolkit for penetration testing of identity verification and video conferencing systems. Supports face swap, image animation, and…

Community-driven catalog of testable security requirements for AI-enabled systems. Provides a structured checklist for developers and security…

MITM HTTP(s) proxy that blocks ads and trackers by intercepting traffic, supporting Adblock Plus filters, uBlock origin syntax, and custom filter…

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

A tool uses Windows Filtering Platform (WFP) to block Endpoint Detection and Response (EDR) agents from reporting security events to the server.

Improve your security and privacy by blocking ads, tracking and malware domains.