
heretic
Fully automatic censorship removal for language models

Fully automatic censorship removal for language models


Programmable guardrails for LLM chat apps: enforce input/output rails, block jailbreaks and prompt injections, detect hallucination, and mask…

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

Linux system-call monitor using ptrace to trace file, process, network, and memory activity, with namespace isolation and machine learning…

A machine learning tool that ranks strings based on their relevance for malware analysis.

A package for capturing and analyzing network flow data and intraflow data, for network research, forensics, and security monitoring.

An Open-Source Package for Textual Adversarial Attack.

Runtime Application Self Protection for Python web servers, serverless functions and MCP servers, detecting attacks, prompt injection and data leaks…

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

Automatic extraction of relevant features from time series:

Streamlit-based insider threat detection prototype using XGBoost and Isolation Forest to analyze employee activity data, generate risk summaries, and…

Reverse Shell Detection with Machine Learning

Image-based Android malware detection framework tackling obfuscation and concept drift. Includes curated datasets and Python code for training…

AI Smart Contract Security Analysis and PoC Generation Framework

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

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