I'm a first year Computer Science Ph.D. student at UC Irvine advised by Sameer Singh. I broadly work on machine learning with focuses on interpretability and fairness.
I did my undergrad at Haverford College and graduated in 2019. During this time, I was fortunate to be advised by Sorelle Friedler, where I researched fairness and interpretability in machine learning.
dslack@uci.edu / @dylanslack20
Papers
-
Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods
Dylan Slack*, Sophie Hilgard*, Emiliy Jia, Sameer Singh, and Himabindu Lakkaraju
AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES), 2020
[Oral Presentation]
Also accepted at SafeAI Workshop, AAAI, 2020
-
Fairness Warnings and Fair-MAML: Learning Fairly with Minimal Data
Dylan Slack, Sorelle Friedler, and Emile Givental
ACM Conference on Fairness, Accountability and Transparency (FAT*), 2020
-
Fairness Warnings
Dylan Slack, Sorelle A Friedler, and Emile Givental
Workshop on Human-Centric Machine Learning, NeurIPS, 2019
-
Fair Meta-Learning: Learning How to Learn Fairly
Dylan Slack, Sorelle A Friedler, and Emile Givental
Workshop on Human-Centric Machine Learning, NeurIPS, 2019
-
Assessing the Local Interpretability of Machine Learning Models
Dylan Slack, Sorelle A Friedler, Carlos Scheidegger, and Chitradeep Dutta Roy
Workshop on Human-Centric Machine Learning, NeurIPS, 2019
* notes equal contribution
Press
Collaborators
Here's an ongoing list of great researchers that I've collaborated with on projects and papers (and their respective links): Hima Lakkaraju (Harvard University), Sophie Hilgard (Harvard University), Emily Jia (Harvard University), Sameer Singh (University of California - Irvine), Emile Givental (Haverford College), Sorelle Friedler (Haverford College), Carlos Scheidegger (University of Arizona), Chitradeep Dutta Roy (University of Utah), Sara Mathieson (Haverford College).