Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Bogdan Kulynych

Bogdan Kulynych

What You See is What You Get: Distributional Generalization for Algorithm Design in Deep Learning



Bogdan Kulynych , Yao-Yuan Yang , Yaodong Yu , Jarosław Błasiok , Preetum Nakkiran

Figure 1 for What You See is What You Get: Distributional Generalization for Algorithm Design in Deep Learning
Figure 2 for What You See is What You Get: Distributional Generalization for Algorithm Design in Deep Learning
Figure 3 for What You See is What You Get: Distributional Generalization for Algorithm Design in Deep Learning
Figure 4 for What You See is What You Get: Distributional Generalization for Algorithm Design in Deep Learning
* First two authors contributed equally 
   Access Paper or Ask Questions

Adversarial for Good? How the Adversarial ML Community's Values Impede Socially Beneficial Uses of Attacks



Kendra Albert , Maggie Delano , Bogdan Kulynych , Ram Shankar Siva Kumar

Figure 1 for Adversarial for Good? How the Adversarial ML Community's Values Impede Socially Beneficial Uses of Attacks
Figure 2 for Adversarial for Good? How the Adversarial ML Community's Values Impede Socially Beneficial Uses of Attacks
* Author list is ordered alphabetically as there is equal contribution. 4 pages Accepted by the ICML 2021 workshop on "A Blessing in Disguise:The Prospects and Perils of Adversarial Machine Learning" 
   Access Paper or Ask Questions

Exploring Data Pipelines through the Process Lens: a Reference Model forComputer Vision



Agathe Balayn , Bogdan Kulynych , Seda Guerses

Figure 1 for Exploring Data Pipelines through the Process Lens: a Reference Model forComputer Vision
Figure 2 for Exploring Data Pipelines through the Process Lens: a Reference Model forComputer Vision
Figure 3 for Exploring Data Pipelines through the Process Lens: a Reference Model forComputer Vision
Figure 4 for Exploring Data Pipelines through the Process Lens: a Reference Model forComputer Vision
* Presented at the CVPR workshop 2021 Beyond Fair Computer Vision 
   Access Paper or Ask Questions

Disparate Vulnerability: on the Unfairness of Privacy Attacks Against Machine Learning



Mohammad Yaghini , Bogdan Kulynych , Carmela Troncoso

Figure 1 for Disparate Vulnerability: on the Unfairness of Privacy Attacks Against Machine Learning
Figure 2 for Disparate Vulnerability: on the Unfairness of Privacy Attacks Against Machine Learning
* Mohammad Yaghini and Bogdan Kulynych contributed equally to this work 
   Access Paper or Ask Questions

Questioning the assumptions behind fairness solutions



Rebekah Overdorf , Bogdan Kulynych , Ero Balsa , Carmela Troncoso , Seda Gürses

* Presented at Critiquing and Correcting Trends in Machine Learning (NeurIPS 2018 Workshop), Montreal, Canada. This is a short version of arXiv:1806.02711 
   Access Paper or Ask Questions

Evading classifiers in discrete domains with provable optimality guarantees



Bogdan Kulynych , Jamie Hayes , Nikita Samarin , Carmela Troncoso

Figure 1 for Evading classifiers in discrete domains with provable optimality guarantees
Figure 2 for Evading classifiers in discrete domains with provable optimality guarantees
Figure 3 for Evading classifiers in discrete domains with provable optimality guarantees
Figure 4 for Evading classifiers in discrete domains with provable optimality guarantees

   Access Paper or Ask Questions

POTs: Protective Optimization Technologies



Rebekah Overdorf , Bogdan Kulynych , Ero Balsa , Carmela Troncoso , Seda Gürses

Figure 1 for POTs: Protective Optimization Technologies
Figure 2 for POTs: Protective Optimization Technologies
Figure 3 for POTs: Protective Optimization Technologies
Figure 4 for POTs: Protective Optimization Technologies
* An earlier version (v1/v2) by Seda G\"urses, Rebekah Overdorf, and Ero Balsa was presented at The Workshop on Hot Topics in Privacy Enhancing Technologies 2018 (HotPETs) and as a Poster at Privacy in Machine Learning and Artificial Intelligence, FAIM Workshop 2018 (PiMLAI) 
   Access Paper or Ask Questions

Feature importance scores and lossless feature pruning using Banzhaf power indices



Bogdan Kulynych , Carmela Troncoso

Figure 1 for Feature importance scores and lossless feature pruning using Banzhaf power indices
* Presented at NIPS 2017 Symposium on Interpretable Machine Learning 
   Access Paper or Ask Questions