Salome Viljoen

Salome Viljoen

Auto-generated profile, based on publicly available information

Salome Viljoen

Center for Internet and Society Harvard University ^Harvard Law School

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2020 in Computer Law & Security Review
Verified
Journal Article
Closed access
MBMoritz Büchi
Moritz Büchi
EVEduard Fosch Villaronga
Eduard Fosch Villaronga
CLChristoph Lutz
Christoph Lutz
ATAurelia Tamò-Larrieux
Aurelia Tamò-Larrieux
SVShruthi Velidi
Shruthi Velidi
SVSalome Viljoen
Salome Viljoen

1 January 2019 in European Data Protection Law Review
Verified
Journal Article
Closed access
PDF file
AFAaron Fluitt
Aaron Fluitt
ACAloni Cohen
Aloni Cohen
MAMicah Altman
Micah Altman
KNKobbi Nissim
Kobbi Nissim
SVSalome Viljoen
Salome Viljoen
AWAlexandra Wood
Alexandra Wood

25 November 2019 in arXiv
Verified
Preprint
Open access
PDF file
RKRam Shankar Siva Kumar
Ram Shankar Siva Kumar
DBDavid O Brien
David O Brien
KAKendra Albert
Kendra Albert
SVSalomé Viljöen
Salomé Viljöen
JSJeffrey Snover
Jeffrey Snover
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.

5 December 2018 in arXiv
Verified
Preprint
Open access
PDF file
RKRam Shankar Siva Kumar
Ram Shankar Siva Kumar
DODavid R. O'Brien
David R. O'Brien
KAKendra Albert
Kendra Albert
SVSalome Vilojen
Salome Vilojen
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.