
delirium-ai-safety-benchmark
A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…
adversarial-attackai-securityeducation+2

A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…

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

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

image scaling attacks for multi-modal prompt injection

Malware Mutation Using Reinforcement Learning and Generative Adversarial Networks

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