Salome Viljoen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Salome Viljoen has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- David R. O'Brien
Center for Internet and Society Harvard University ^Harvard Law School
2 shared publications - Kendra Albert
Center for Internet and Society Harvard University ^Harvard Law School
2 shared publications - Ram Shankar Siva Kumar
Microsoft Redmond USA
2 shared publications Aaron Fluitt
1 shared publication- Alexandra Wood1 shared publication
- Aloni Cohen
University of Chicago
1 shared publication
Latest Publications
- 1 April 2020
- Published by Elsevier in Computer Law & Security Review
- Vol. 36
The chilling effects of algorithmic profiling: Mapping the issues
- 1 April 2020
- Published by Elsevier in Computer Law & Security Review
- Vol. 36
The chilling effects of algorithmic profiling: Mapping the issues
- Open Access
Failure Modes in Machine Learning Systems
In the last two years, more than 200 papers have been written on how machine learning (ML) systems can fail because of adversarial attacks on the algorithms and data; this number balloons if we were to incorporate papers covering non-adversarial failure modes. The spate of papers has made it difficult for ML practitioners, let alone engineers, lawyers, and policymakers, to keep up with the attacks against and defenses of ML systems. However, as these systems become more pervasive, the need to understand how they fail, whether by the hand of an adversary or due to the inherent design of a system, will only become more pressing. In order to equip software developers, security incident responders, lawyers, and policy makers with a common vernacular to talk about this problem, we developed a framework to classify failures into "Intentional failures" where the failure is caused by an active adversary attempting to subvert the system to attain her goals; and "Unintentional failures" where the failure is because an ML system produces an inherently unsafe outcome. After developing the initial version of the taxonomy last year, we worked with security and ML teams across Microsoft, 23 external partners, standards organization, and governments to understand how stakeholders would use our framework. Throughout the paper, we attempt to highlight how machine learning failure modes are meaningfully different from traditional software failures from a technology and policy perspective.
Open AccessFailure Modes in Machine Learning Systems
In the last two years, more than 200 papers have been written on how machine learning (ML) systems can fail because of adversarial attacks on the algorithms and data; this number balloons if we were to incorporate papers covering non-adversarial failure modes. The spate of papers has made it difficult for ML practitioners, let alone engineers, lawyers, and policymakers, to keep up with the attacks against and defenses of ML systems. However, as these systems become more pervasive, the need to understand how they fail, whether by the hand of an adversary or due to the inherent design of a system, will only become more pressing. In order to equip software developers, security incident responders, lawyers, and policy makers with a common vernacular to talk about this problem, we developed a framework to classify failures into "Intentional failures" where the failure is caused by an active adversary attempting to subvert the system to attain her goals; and "Unintentional failures" where the failure is because an ML system produces an inherently unsafe outcome. After developing the initial version of the taxonomy last year, we worked with security and ML teams across Microsoft, 23 external partners, standards organization, and governments to understand how stakeholders would use our framework. Throughout the paper, we attempt to highlight how machine learning failure modes are meaningfully different from traditional software failures from a technology and policy perspective.
- 1 January 2019
- Published by Lexxion Verlag in European Data Protection Law Review
- Vol. 5 (3) , 285-292
Opinions ∙ Data Protection’s Composition Problem
- 1 January 2019
- Published by Lexxion Verlag in European Data Protection Law Review
- Vol. 5 (3) , 285-292
Opinions ∙ Data Protection’s Composition Problem
- Open Access
Law and Adversarial Machine Learning
When machine learning systems fail because of adversarial manipulation, how should society expect the law to respond? Through scenarios grounded in adversarial ML literature, we explore how some aspects of computer crime, copyright, and tort law interface with perturbation, poisoning, model stealing and model inversion attacks to show how some attacks are more likely to result in liability than others. We end with a call for action to ML researchers to invest in transparent benchmarks of attacks and defenses; architect ML systems with forensics in mind and finally, think more about adversarial machine learning in the context of civil liberties. The paper is targeted towards ML researchers who have no legal background.
Open AccessLaw and Adversarial Machine Learning
When machine learning systems fail because of adversarial manipulation, how should society expect the law to respond? Through scenarios grounded in adversarial ML literature, we explore how some aspects of computer crime, copyright, and tort law interface with perturbation, poisoning, model stealing and model inversion attacks to show how some attacks are more likely to result in liability than others. We end with a call for action to ML researchers to invest in transparent benchmarks of attacks and defenses; architect ML systems with forensics in mind and finally, think more about adversarial machine learning in the context of civil liberties. The paper is targeted towards ML researchers who have no legal background.