
heretic
Fully automatic censorship removal for language models

Fully automatic censorship removal for language models

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

Open framework for RL-based prompt injection red teaming, with a shared trainer, curriculum learning, and benchmarks like AgentDojo, InjecAgent, and…

Web-based adversary emulation platform that orchestrates Atomic Red Team tests across Windows endpoints via Go agents, with MITRE ATT&CK mapping, APT…

Reverse Shell Detection with Machine Learning

Playbook-based adversary simulation framework that compiles JSON-defined attack paths into position-independent shellcode payloads for validating…

Causal context attribution and rule-based monitor LLM defense against indirect prompt injection in LLM agents, achieving state-of-art performance on…

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

A novel adversarial attack on LLM based on the Exponentiated Gradient Descent technique.

An Open-Source Package for Textual Adversarial Attack.

Red Team K8S Adversary Emulation Based on kubectl