Why_this_webapp Bibliography

The Different Faces of AI Ethics Across the World: A Principle-Implementation Gap Analysis / 2206.03225 / on (web) Publishing site

5 Evaluation of Ethical Principle Implementations

Dual Governance: The intersection of centralized regulation and crowdsourced safety mechanisms for Generative AI / 2308.04448 / on (web) Publishing site

5 Crowdsourced safety mechanism

Bad, mad, and cooked: Moral responsibility for civilian harms in human-AI military teams / 2211.06326 / on (web) Publishing site

Responsibility in War
Moral Injury

A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation / 2305.11391 / on (web) Publishing site

2 Large Language Models
5 Falsification and Evaluation
Reference

Getting pwn'd by AI: Penetration Testing with Large Language Models / 2308.00121 / on (web) Publishing site

1 Introduction

The Promise and Peril of Artificial Intelligence -- Violet Teaming Offers a Balanced Path Forward / 2308.14253 / on (web) Publishing site

Abstract
1 Introduction
4 Integrating red teaming, blue teaming, and ethics with violet teaming
5 Research directions in AI safety and violet teaming
6 A pathway for balanced AI innovation
7 Violet teaming to address dual-use risks of AI in biotechnology
8 Macrostrategy for responsible technology trajectories
9 The path forward
10 Supplemental & additional details
References