
heretic
Fully automatic censorship removal for language models

Fully automatic censorship removal for language models

Adversary Emulation Framework

Empire is a post-exploitation and adversary emulation framework that is used to aid Red Teams and Penetration Testers.

AI-assisted research pipeline that extracts HTTP desync techniques, generates malformed request test-cases, validates them via Burp, and confirms…

Agentic jailbreak framework for LLM-based agents using scheme-based task decomposition, multi-turn disguising strategies, and adaptive self-evolution…

Bypass llm guardrails by confusing it with fabricated tool output.

During the exploitation phase of a pen test or ethical hacking engagement, you will ultimately need to try to cause code to run on target system…

Collection of CVE(work) on tenserflow binary pwning it

Experiments for control-token chain-of-thought suppression and parser-leniency attacks on tool-using LLM agents

Crystal port of GodPotato to abuse SeImpersonatePrivilege with indirect syscalls, dynamic API resolution and compile-time string obfuscation. Run…

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

Proof-of-concept and technical analysis of CVE-2025-0411, a 7-Zip Mark-of-the-Web bypass vulnerability exploited in SmokeLoader campaigns, with…

Simple (relatively) things allowing you to dig a bit deeper than usual.

Malware Mutation Using Reinforcement Learning and Generative Adversarial Networks

A POC for the new injection technique, abusing windows fork API to evade EDRs. https://www.blackhat.com/eu-22/briefings/schedule/index.html#dirty-vani…

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

A DNS spoofer tool written in Python3.

This repository contains detailed adversary simulation APT campaigns targeting various critical sectors. Each simulation includes custom tools, C2…