
caldera
Automated Adversary Emulation Platform
adversarial-attackcommand-and-controlctf+7

Automated Adversary Emulation Platform

Automated behavioral evaluation framework for LLMs that generates diverse test scenarios to probe for sycophancy, bias, and other safety-relevant…

Data from a BRAWL Automated Adversary Emulation Exercise

Automated framework for hijacking safety reasoning in large reasoning models via simulated reasoning traces and iterative prompt refinement to…

An alignment auditing agent capable of quickly exploring alignment hypothesis

Attempt at Obfuscated version of SharpCollection

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

C2 redirector base on caddy