Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 4 of 4
Full-Text Articles in Law
Legal Risks Of Adversarial Machine Learning Research, Ram Shankar Siva Kumar, Jonathon Penney, Bruce Schneier, Kendra Albert
Legal Risks Of Adversarial Machine Learning Research, Ram Shankar Siva Kumar, Jonathon Penney, Bruce Schneier, Kendra Albert
Articles, Book Chapters, & Popular Press
Adversarial machine learning is the systematic study of how motivated adversaries can compromise the confidentiality, integrity, and availability of machine learning (ML) systems through targeted or blanket attacks. The problem of attacking ML systems is so prevalent that CERT, the federally funded research and development center tasked with studying attacks, issued a broad vulnerability note on how most ML classifiers are vulnerable to adversarial manipulation. Google, IBM, Facebook, and Microsoft have committed to investing in securing machine learning systems. The US and EU are likewise putting security and safety of AI systems as a top priority.
Now, research on adversarial …
Politics Of Adversarial Machine Learning, Kendra Albert, Jonathon Penney, Bruce Schneier, Ram Shankar Siva Kumar
Politics Of Adversarial Machine Learning, Kendra Albert, Jonathon Penney, Bruce Schneier, Ram Shankar Siva Kumar
Articles, Book Chapters, & Popular Press
In addition to their security properties, adversarial machine-learning attacks and defenses have political dimensions. They enable or foreclose certain options for both the subjects of the machine learning systems and for those who deploy them, creating risks for civil liberties and human rights. In this paper, we draw on insights from science and technology studies, anthropology, and human rights literature, to inform how defenses against adversarial attacks can be used to suppress dissent and limit attempts to investigate machine learning systems. To make this concrete, we use real-world examples of how attacks such as perturbation, model inversion, or membership inference …
Implementing User Rights For Research In The Field Of Artificial Intelligence: A Call For International Action, Sean Flynn, Christophe Geiger, Joao Pedro Quintais, Thomas Margoni, Matthew Sag, Lucie Guibault, Michael W. Carroll
Implementing User Rights For Research In The Field Of Artificial Intelligence: A Call For International Action, Sean Flynn, Christophe Geiger, Joao Pedro Quintais, Thomas Margoni, Matthew Sag, Lucie Guibault, Michael W. Carroll
Articles, Book Chapters, & Popular Press
Last year, before the onset of a global pandemic highlighted the critical and urgent need for technology-enabled scientific research, the World Intellectual Property Organization (WIPO) launched an inquiry into issues at the intersection of intellectual property (IP) and artificial intelligence (AI). We contributed comments to that inquiry, with a focus on the application of copyright to the use of text and data mining (TDM) technology. This article describes some of the most salient points of our submission and concludes by stressing the need for international leadership on this important topic. WIPO could help fill the current gap on international leadership, …
Ethical Testing In The Real World: Evaluating Physical Testing Of Adversarial Machine Learning, Kendra Albert, Maggie Delano, Jonathon Penney, Afsaneh Ragot, Ram Shankar Siva Kumar
Ethical Testing In The Real World: Evaluating Physical Testing Of Adversarial Machine Learning, Kendra Albert, Maggie Delano, Jonathon Penney, Afsaneh Ragot, Ram Shankar Siva Kumar
Articles, Book Chapters, & Popular Press
This paper critically assesses the adequacy and representativeness of physical domain testing for various adversarial machine learning (ML) attacks against computer vision systems involving human subjects. Many papers that deploy such attacks characterize themselves as “real world.” Despite this framing, however, we found the physical or real-world testing conducted was minimal, provided few details about testing subjects and was often conducted as an afterthought or demonstration. Adversarial ML research without representative trials or testing is an ethical, scientific, and health/safety issue that can cause real harms. We introduce the problem and our methodology, and then critique the physical domain testing …