86 citations · 387 across the 45 of their papers we have counts for
7 papers · 1 filter
Questioning the assumptions behind fairness solutions
Rebekah Overdorf, Bogdan Kulynych, Ero Balsa +2
In addition to their benefits, optimization systems can have negative economic, moral, social, and political effects on populations as well as their environments. Frameworks like f…
Evading classifiers in discrete domains with provable optimality guarantees
Bogdan Kulynych, Jamie Hayes, Nikita Samarin +1
Machine-learning models for security-critical applications such as bot, malware, or spam detection, operate in constrained discrete domains. These applications would benefit from h…
Rethinking Location Privacy for Unknown Mobility Behaviors
Simon Oya, Carmela Troncoso, Fernando Pérez-González
Location Privacy-Preserving Mechanisms (LPPMs) in the literature largely consider that users' data available for training wholly characterizes their mobility patterns. Thus, they h…
Tandem: Securing Keys by Using a Central Server While Preserving Privacy
Wouter Lueks, Brinda Hampiholi, Greg Alpár +1
Users' devices, e.g., smartphones or laptops, are typically incapable of securely storing and processing cryptographic keys. We present Tandem, a novel set of protocols for securin…
POTs: Protective Optimization Technologies
Bogdan Kulynych, Rebekah Overdorf, Carmela Troncoso +1
Algorithmic fairness aims to address the economic, moral, social, and political impact that digital systems have on populations through solutions that can be applied by service pro…
Under the Underground: Predicting Private Interactions in Underground Forums
Rebekah Overdorf, Carmela Troncoso, Rachel Greenstadt +1
Underground forums where users discuss, buy, and sell illicit services and goods facilitate a better understanding of the economy and organization of cybercriminals. Prior work has…