- Mnih, V. et al. Human-level control through deep reinforcement learning. Nature 518 (Feb. 26, 2015), 529--533.Google ScholarCross Ref
- Xiong, W. et al. Achieving human parity in conversational speech recognition. arXiv (Feb. 17, 2017); https://arxiv.org/abs/1610.05256Google Scholar
- Cook, S.A. and Dwork, C. Bounds on the time for parallel RAM's to compute simple functions. In Proceedings of the 14th Annual ACM Symposium on Theory of Computing (San Francisco, CA, May 5--7). ACM Press, New York, 1982, 231--233. Google ScholarDigital Library
- Fich, F.E., Meyer auf der Heide, F., Ragde, P., and Wigderson, A. One, two, three … infinity: Lower bounds for parallel computation. In Proceedings of the 17th Annual ACM Symposium on Theory of Computing (Providence, RI, May 6--8). ACM Press, New York, 1985, 48--58. Google ScholarDigital Library
Index Terms
- Consider indirect threats of AI, too
Recommendations
Artificial Intelligence Security: Threats and Countermeasures
In recent years, with rapid technological advancement in both computing hardware and algorithm, Artificial Intelligence (AI) has demonstrated significant advantage over human being in a wide range of fields, such as image recognition, education, ...
Insider Threats: It's the HUMAN, Stupid!
NCS '19: Proceedings of the Northwest Cybersecurity SymposiumInsider threats refer to threats posed by individuals who intentionally or unintentionally destroy, exfiltrate, or leak sensitive information, or expose their organization to outside attacks. Surveys of organizations in government and industry ...
Hardware-based cyber threats: attack vectors and defence techniques
There are certain vulnerabilities associated with computing hardware that attackers can exploit to launch destructive attacks which often go undetected by the existing hardware and software countermeasures. Side channel attacks (SCAs) and Rowhammer ...
Comments