Background: Science is experiencing a reproducibility crisis. Artificial intelligence research is not an exception. Objective: To give practical and pragmatic recommendations for how to document AI research so that the results are reproducible. Method: Our analysis of the literature shows that AI publications fall short of providing enough documentation to facilitate reproducibility. Our suggested best practices are based on a framework for reproducibility and recommendations given for other disciplines. Results: We have made an author checklist based on our investigation and provided examples for how every item in the checklist can be documented. Conclusion: We encourage reviewers to use the suggested best practices and author checklist when reviewing submissions for AAAI publications and future AAAI conferences.

Intelligent systems rely on pattern recognition and signature-based approaches for a wide range of sensors enhancing situational awareness. For example, autonomous systems depend on environmental sensors to perform their tasks and secure systems depend on anomaly detection methods. The availability of large amount of data requires the processing of data in a “streaming” fashion with online algorithms. Yet, just as online learning can enhance adaptability to a non-stationary environment, it introduces vulnerabilities that can be manipulated by adversaries to achieve their goals while evading detection. Although human intelligence might have evolved from social interactions, machine intelligence has evolved as a human intelligence artifact and been kept isolated to avoid ethical dilemmas. As our adversaries become sophisticated, it might be time to revisit this question and examine how we can combine online learning and reasoning leading to the science of deceptive and counter-deceptive machines.

Abstract recognizing Web browsing signatures can complement other behavioral biometrics such as keystroke authentication to verify a claim of identity and/or identify persons of interest. The deluge of available digital traces enables the cognitive analysis of behavioral traits that differentiate between users and predict their online behavior. Recommendation systems have long capitalized on this capability to personalize search queries but have not exploited the temporal structure of preferences. This paper claims that spatio-temporal patterns of category of website visited by time of access can uniquely characterize and identify users. We present some exploratory approaches in user identification based on recurrent neural networks and empirical results based on clickstream data obtained through a user study and through an internet data provider.