Giuseppe Cascavilla
ABSTRACT
Simulating terrorist scenarios in cyber-physical spaces---that is, urban open or (semi-) closed spaces combined with cyber-physical systems counterparts---is challenging given the context and variables therein. This paper addresses the aforementioned issue with ALTer a framework featuring computer vision and Generative Adversarial Neural Networks (GANs) over terrorist scenarios. We obtained the data for the terrorist scenarios by creating a synthetic dataset, exploiting the Grand Theft Auto V (GTAV) videogame, and the Unreal Game Engine behind it, in combination with OpenStreetMap data. The results of the proposed approach show its feasibility to predict criminal activities in cyber-physical spaces. Moreover, the usage of our synthetic scenarios elicited from GTAV is promising in building datasets for cybersecurity and Cyber-Threat Intelligence (CTI) featuring simulated video gaming platforms. We learned that local authorities can simulate terrorist scenarios for their cities based on previous or related reference and this helps them in 3 ways: (1) better determine the necessary security measures; (2) better use the expertise of the authorities; (3) refine preparedness scenarios and drills for sensitive areas.
- Rameen Abdal, Yipeng Qin, and Peter Wonka. 2019. Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space? arXiv: cs.CV/1904.03189Google Scholar
- David Bau, Jun-Yan Zhu, Hendrik Strobelt, Bolei Zhou, Joshua B. Tenenbaum, William T. Freeman, and Antonio Torralba. 2018. GAN Dissection: Visualizing and Understanding Generative Adversarial Networks. arXiv:cs.CV/1811.10597Google Scholar
- Daniel Birks, Michael Townsley, and Anna Stewart. 2012. Generative explanations of crime: Using simulation to test criminological theory. Criminology 50, 1 (2012), 221--254.Google ScholarCross Ref
- Tibor Bosse and Charlotte Gerritsen. 2009. Comparing crime prevention strategies by agent-based simulation. In 2009 IEEE /WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, Vol. 2. IEEE, 491--496.Google ScholarDigital Library
- Andrew Brock, Jeff Donahue, and Karen Simonyan. 2018. Large Scale GAN Training for High Fidelity Natural Image Synthesis. arXiv:cs.LG/1809.11096Google Scholar
- Gerald G Brown and Louis Anthony Cox, Jr. 2011. How probabilistic risk assessment can mislead terrorism risk analysts. Risk Analysis: An International Journal 31, 2 (2011), 196--204.Google ScholarCross Ref
- Rosaria Conte, Rainer Hegselmann, and Pietro Terna. 2013. Simulating social phenomena. Vol. 456. Springer Science & Business Media.Google Scholar
- Nelson Devia and Richard Weber. 2013. Generating crime data using agent-based simulation. Computers, Environment and Urban Systems 42 (2013), 26--41. https://doi.org/10.1016/j.compenvurbsys.2013.09.001Google ScholarCross Ref
- Jeff Donahue, Philipp Krähenbühl, and Trevor Darrell. 2016. Adversarial feature learning. arXiv preprint arXiv:1605.09782 (2016).Google Scholar
- Vincent Dumoulin, Ishmael Belghazi, Ben Poole, Olivier Mastropietro, Alex Lamb, Martin Arjovsky, and Aaron Courville. 2016. Adversarially learned inference. arXiv preprint arXiv:1606.00704 (2016).Google Scholar
- Barry Charles Ezell, Steven P Bennett, Detlof Von Winterfeldt, John Sokolowski, and Andrew J Collins. 2010. Probabilistic risk analysis and terrorism risk. Risk Analysis: An International Journal 30, 4 (2010), 575--589.Google ScholarCross Ref
- Stanley Friedman. 1982. Contingency and disaster planning. Computers & Security 1, 1 (1982), 34--40.Google ScholarCross Ref
- Aviv Gabbay and Yedid Hoshen. 2019. Style Generator Inversion for Image Enhancement and Animation. arXiv preprint arXiv:1906.11880 (2019).Google Scholar
- Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge. 2015. A Neural Algorithm of Artistic Style. CoRR abs/1508.06576 (2015). http://arxiv.org/abs/1508.06576Google Scholar
- Leon A Gatys, Alexander S Ecker, and Matthias Bethge. 2016. Image style transfer using convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2414--2423.Google ScholarCross Ref
- Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In Advances in Neural Information Processing Systems 27, Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, and K. Q. Weinberger (Eds.). Curran Associates, Inc., 2672--2680. http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdfGoogle ScholarDigital Library
- Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative Adversarial Networks. http://arxiv.org/abs/1406.2661 cite arxiv:1406.2661.Google Scholar
- J. Hamari, J. Koivisto, and H. Sarsa. 2014. Does Gamification Work? - A Literature Review of Empirical Studies on Gamification. In 2014 47th Hawaii International Conference on System Sciences. 3025--3034. https://doi.org/10.1109/HICSS.2014.377Google ScholarDigital Library
- Mengmeng Hao, Dong Jiang, Fangyu Ding, Jingying Fu, and Shuai Chen. 2019. Simulating Spatio-Temporal Patterns of Terrorism Incidents on the Indochina Peninsula with GIS and the Random Forest Method. ISPRS International Journal of Geo-Information 8, 3 (2019), 133.Google ScholarCross Ref
- Isaias Hoyos, Bruno Esposito, and Miguel Núñez del Prado. 2018. DETECTOR: Automatic Detection System for Terrorist Attack Trajectories.. In SIMBig (Communications in Computer and Information Science), Juan Antonio Lossio-Ventura, Denisse Muñante, and Hugo Alatrista-Salas (Eds.), Vol. 898. Springer, 160--173.Google Scholar
- Po-Han Huang, Kevin Matzen, Johannes Kopf, Narendra Ahuja, and Jia-Bin Huang. 2018. DeepMVS: Learning Multi-View Stereopsis. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google Scholar
- Tero Karras, Samuli Laine, and Timo Aila. 2019. A Style-Based Generator Architecture for Generative Adversarial Networks. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://github.com/NVlabs/styleganGoogle ScholarCross Ref
- Tero Karras, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. 2019. Analyzing and Improving the Image Quality of StyleGAN. CoRR abs/1912.04958 (2019).Google Scholar
- Jingyu Liu, Walter W Piegorsch, A Grant Schissler, and Susan L Cutter. 2018. Autologistic models for benchmark risk or vulnerability assessment of urban terrorism outcomes. Journal of the Royal Statistical Society: Series A (Statistics in Society) 181, 3 (2018), 803--823.Google ScholarCross Ref
- Junyu Luo, Yong Xu, Chenwei Tang, and Jiancheng Lv. 2017. Learning inverse mapping by autoencoder based generative adversarial nets. In International Conference on Neural Information Processing. Springer, 207--216.Google ScholarCross Ref
- Vivek Menon, Bharat Jayaraman, and Venu Govindaraju. 2011. The Three Rs of Cyberphysical Spaces. IEEE Computer 44, 9 (2011), 73--79.Google ScholarDigital Library
- Il-Chul Moon and Kathleen M. Carley. 2007. Modeling and Simulating Terrorist Networks in Social and Geospatial Dimensions. IEEE Intelligent Systems 22, 5 (2007), 40--49.Google ScholarDigital Library
- Shital Shah, Debadeepta Dey, Chris Lovett, and Ashish Kapoor. 2017. AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles. In Field and Service Robotics. arXiv:arXiv:1705.05065 https://arxiv.org/abs/1705.05065Google Scholar
- Yujun Shen, Jinjin Gu, Xiaoou Tang, and Bolei Zhou. 2019. Interpreting the latent space of gans for semantic face editing. arXiv preprint arXiv:1907.10786 (2019).Google Scholar
- Dimitris Spiliotopoulos, Costas Vassilakis, and Dionisis Margaris. 2019. Data-driven country safety monitoring terrorist attack prediction.. In ASONAM, Francesca Spezzano, Wei Chen, and Xiaokui Xiao (Eds.). ACM, 1128--1135.Google Scholar
- Kayo Yin. 2019. How to Train StyleGAN to Generate Realistic Faces. https://bit.ly/2FQ0CU7.Google Scholar
Index Terms
- Counterterrorism for Cyber-Physical Spaces: A Computer Vision Approach
Recommendations
Investigative data mining and its application in counterterrorism
AIC'05: Proceedings of the 5th WSEAS International Conference on Applied Informatics and CommunicationsIt is well recognized that advanced filtering and mining in information streams and intelligence bases are of key importance in investigative analysis for countering terrorism and organized crime. As opposed to traditional data mining aiming at ...
Architecting dynamic cyber-physical spaces
We increasingly live in cyber-physical spaces: spaces that are both physical and digital, and where the two aspects are intertwined. Cyber-physical spaces may exhibit a range of behaviors, from smart control of heating, ventilation, and light to ...
Preventing Cyber-induced Irreversible Physical Damage to Cyber-Physical Systems
CISR '15: Proceedings of the 10th Annual Cyber and Information Security Research ConferenceEver since the discovery of the Stuxnet malware, there have been widespread concerns about disasters via cyber-induced physical damage on critical infrastructures. Cyber physical systems (CPS) integrate computation and physical processes; such ...
Comments