Stars
Red AI Archive: Jeff Sims - A curated collection of work in AI safety, cybersecurity data science, and AI red teaming – my own research alongside academic and industry peer research which have reco…
Stage 1: Sensitive Email/Chat Classification for Adversary Agent Emulation (espionage). This project is meant to extend Red Reaper v1 which was presented at RSA San Francisco 2024.
A curated list of GPT agents for cybersecurity
5
Updated Nov 12, 2023
A method to adversarially assess the Phi-3 Instruct model by observing the attention distribution across its heads when exposed to specific inputs. This approach prompts the model to adopt the 'dev…