
ml-CVE-2023-1177
Machine learning-based exploit for CVE-2023-1177 vulnerability, enabling automated security testing and exploitation of the identified flaw.

Machine learning-based exploit for CVE-2023-1177 vulnerability, enabling automated security testing and exploitation of the identified flaw.

An interactive CLI application for interacting with authenticated Jupyter instances.

A minimal LLM-powered zero-day vulnerability scanner by AISLE.

PoC code from DEF CON 25 presentation

Malware Mutation Using Reinforcement Learning and Generative Adversarial Networks

A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)

takes shellcode bad-bytes and banishes them, returning cleaned shellcode with preserved functionalities

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

This repository provides the official implementation of POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models.

Proof-of-concept that poisons MLflow registered models via the REST API, embedding a malicious pickle to trigger RCE when the model is loaded.

AST-based Static Code Analyzer with Agentic LLM-Powered Relationship Mapping to discover Python RCE paths and deep deserialization chains on AI, LLM,…

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

Python library for local LLM-powered security analysis with Ghidra binary analysis, C/C++ vulnerability scanning, and MCP tool integration for…

Collection of CVE(work) on tenserflow binary pwning it

Proof-of-concept exploit for CVE-2025-32434, a pickle deserialization vulnerability in PyTorch's weights_only mode, demonstrating malicious tar file…

Real-time anomaly detection system for Apache Struts CVE-2017-5638 exploit using streaming analytics, 3-gram byte analysis, and Count-Min Sketch.…

Taxonomy-guided adaptive red teaming framework that sweeps prompt-injection techniques and refines failed attempts to find diverse attacks against…

Automating Host Exploitation with AI