Adversarial ML Attack that Secretly Gives a Language Model a Point of View
Adversarial ML Attack that Secretly Gives a Language Model a Point of View – Schneier on Security
Category: Machine Learning
Blueprint for AI Bill of Rights pushlished by Office of Science and Technology Policy (OSTP)
More information can be found on https://www.whitehouse.gov/ostp/ai-bill-of-rights/ and https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf The document outlines 5 core areas of concern: Safe and Effective Systems Algorithmic Discrimination Protection Data Privacy Notice and…
1st Trustworthy and Ethical Machine Learning Workshop
We held our workshop at TransAI last week with an excellent reception. While we only had 2 research papers focused on trustworthy machine learning, the discussion focused on…
Guidelines for Ethical Modeling of Algorithms
As part of NumFocus and for PyData 2017 Conference a number of resources and guidelines for ethical modeling of algorithms have been released. Besides and expanded view and…
Fujitsu Delivers New AI Ethics Resource Toolkit
Fujitsu Delivers New AI Ethics Resource Toolkit
White House Scientific Integrity Report Addresses AI and ML Ethics
https://www.hpcwire.com/2022/01/26/white-house-scientific-integrity-report-addresses-ai-and-ml-ethics
Robustness and Explainability of Artificial Intelligence
In anticipation of potential negative consequences when employing artificial intelligence (AI) the European Commission Joint Research Centre (JRC) published a technical report offering a policy-oriented description of the…