A Trilogy of AI Safety Frameworks: Paths from Facts and Knowledge Gaps to Reliable Predictions and New Knowledge

Simon Kasif
10/9/2024
cs.AI

No confident code implementation found for this paper.

Abstract

AI Safety has become a vital front-line concern of many scientists within and outside the AI community. There are many immediate and long term anticipated risks that range from existential risk to human existence to deep fakes and bias in machine learning systems [1-5]. In this paper, we reduce the full scope and immense complexity of AI safety concerns to a trilogy of three important but tractable opportunities for advances that have the short-term potential to improve AI safety and reliability without reducing AI innovation in critical domains. In this perspective, we discuss this vision based on several case studies that already produced proofs of concept in critical ML applications in biomedical science.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Logic-Based Explainability: Past, Present & Future

86% match2024

Report on NSF Workshop on Science of Safe AI

85% match2025

Foundation Models in Biomedical Imaging: Turning Hype into Reality

83% match2025

Prioritizing High-Consequence Biological Capabilities in Evaluations of Artificial Intelligence Models

83% match2024

Towards Trustworthy AI: A Review of Ethical and Robust Large Language Models

83% match2024

Computing in the Life Sciences: From Early Algorithms to Modern AI

82% match1 repo2024

Cite this paper

@article{kasif2024trilogy,
  title  = {A Trilogy of AI Safety Frameworks: Paths from Facts and Knowledge Gaps to Reliable Predictions and New Knowledge},
  author = {Simon Kasif},
  year   = {2024},
  eprint = {2410.06946},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.06946v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.06946.svg)](https://codeofpaper.com/paper/2410.06946)

Discussion