References
- [1] Danzig, R. Technology Roulette: Managing Loss of Control as Many Militaries Pursue Technological Superiority. Tech. rep., Center for a New American Security, 2018.
- [2] Hanson, R. The Age of Em: Work, Love, and Life when Robots Rule the Earth. Oxford University Press, 2016.
- [3] Jagielski, M., Oprea, A., Biggio, B., Liu, C., Nita-Rotaru, C., and Li, B. Manipulating machine learning: Poisoning attacks and countermeasures for regression learning. arXiv preprint arXiv:1804.00308 (2018).
- [4] Kasparov, G. The chess master and the computer. The New York Review of Books 57, 2 (2010), 16–19.
- [5] Li, B., Wang, Y., Singh, A., and Vorobeychik, Y. Data Poisoning Attacks on Factorization-Based Collaborative Filtering. aug 2016.
- [6] Manheim, D. Overoptimization Failures and Specification Gaming in Multi-agent Systems. arXiv preprint arXiv:1810.10862 (2018).
- [7] Mei, Y. Efficient scalable schemes for monitoring a large number of data streams. Biometrika 97, 2 (jun 2010), 419–433.
- [8] Paul, C., Clarke, C. P., Triezenberg, B. L., Manheim, D., and Wilson, B. Automation, Machine Learning, and Computational Propaganda. In Requirements for Better C2 and Situational Awareness of the Information Environment. RAND Corporation, 2018, ch. Appendix.
- [9] Schwartz, O. Competing Visions for AI. Digital Culture & Society 4, 1 (2018), 87–106.
- [10] Shafahi, A., Huang, W. R., Studer, C., Feizi, S., and Goldstein, T. Are adversarial examples inevitable? arXiv preprint arXiv:1809.02104 (2018).
- [11] Shalev-Shwartz, S., Shammah, S., and Shashua, A. On a formal model of safe and scalable self-driving cars. arXiv preprint arXiv:1708.06374 (2017).
- [12] Shorter, G. W., and Miller, R. S. High-frequency trading: background, concerns, and regulatory developments, vol. 29. Congressional Research Service Washington, DC, 2014.
- [13] Yudkowsky, E. The AI Alignment Problem: Why It’s Hard, and Where to Start. In Symbolic Systems Distinguished Speaker (2016), Stanford University.