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

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

A tool for generating .NET serialized gadgets that can trigger .NET assembly load/execution when deserialized using BinaryFormatter from JS/VBS/VBA…

Bypass llm guardrails by confusing it with fabricated tool output.

This is the tool to dump the LSASS process on modern Windows 11

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

A DNS spoofer tool written in Python3.

image scaling attacks for multi-modal prompt injection

Abuses Windows Filtering Platform to launch a console as NT AUTHORITY\SYSTEM or impersonate another logged-on user for privilege escalation during…

Malware Mutation Using Reinforcement Learning and Generative Adversarial Networks

Exploits the Windows Server 2025 dMSA privilege escalation vulnerability to enumerate writable OUs, escalate to arbitrary domain users, extract…

A payload delivery system which embeds payloads in an executable's icon file!

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