Sumon Biswas
Sumon Biswas
Home
Publication
Service
Projects
Teaching
News
Blogs
Contact
Light
Dark
Automatic
long-term
FairSense: Long-Term Fairness Analysis of ML-Enabled Systems
We propose a simulation-based framework called FairSense to detect and analyze long-term unfairness in ML-enabled systems.
Yining She
,
Sumon Biswas
,
Christian Kästner
,
Eunsuk Kang
Cite
Code
DOI
PDF
Long-Term Risks in ML Systems
This project investigates how feedback loops in ML systems can cause long-term, harmful impacts, and develops tools to detect, analyze, and prevent them before deployment.
Towards Safe ML-Based Systems in Presence of Feedback Loops
We highlight the safety risks posed by feedback loops in ML-based systems, discuss why they are hard to detect with current software engineering methods, and propose research directions to better identify, monitor, and mitigate these effects.
Sumon Biswas
,
Yining She
,
Eunsuk Kang
Cite
DOI
PDF
Cite
×