Software systems increasingly support communities of users who interact through the platform, which elevates the importance and impact of research on integrity and privacy. How do we ensure that such communities remain safe and that their data remains private?
To tackle these challenges, Facebook is undertaking research and development on a Web-Enabled Simulation (WES) system called WW. WW is a multiagent simulation that trains agents (bots) using automated learning and optimization to simulate the social behavior of a range of good and bad actors. The simulation aims to automatically find and fix integrity and privacy issues.
In this RFP, we are particularly interested in research that tackles the aforementioned challenges and could also lead to collaboration with our WW project.
“The WW team combines advanced research, practical software engineering, and machine learning,” says Mark Harman, Research Scientist at Facebook on the WW project. “We are really excited to work with, learn from, and contribute to the wealth of science that underpins WW. We hope that collaboration with the academic community will foster and strengthen research partnerships and that it will accelerate academic research adoption and impact.”
Topics of interest for this RFP include, but are not limited to, the following:
- AI-assisted gameplay
- Causal inference
- Evolutionary computation
- Game theory, graph theory
- Information theory
- Machine learning
- Multiagent systems
- Predictive modeling
- Programming languages
- Search-based software engineering
- Software repository mining
- Software testing (in particular, social testing)
The deadline to apply is July 15, 2020, at 5:00 pm AOE. We plan to distribute 3 to 8 awards, each in the $50,000 range. For more information, including topics of interest, eligibility, and proposal requirements, visit the application page.