Paulo Shakarian

Shakarian was a major in the U.S Army serving from 2002 to 2014, undertaking two combat tours in Iraq and earning a Bronze Star and the Army Commendation Medal for valor.{{Cite web|url=https://isearch.asu.edu/profile/2424157|title=Paulo Shakarian {{!}} iSearch|website=isearch.asu.edu|access-date=2019-08-07}} While in the army he was trained in Information assurance and completed a bachelor's degree in computer science at the U.S. Military Academy. In 2007 he served as a military fellow at Defense Advanced Research Projects Agency (DARPA). While in uniform, he went on to study a master's degree in computer science at the University of Maryland in 2009, and later a PhD in 2011 under the advisement of V.S. Subrahmanian.{{Cite web|url=https://vssubrah.github.io/|title=Home | VS Subrahmanian|website=vssubrah.github.io}} His Ph.D. was focused on symbolic artificial intelligence, in particular logic programming, temporal logic, and abductive inference.{{cite web |last1=Shakarian |first1=Paulo |title=Spatio-Temporal Reasoning about Agent Behavior |date=2011 |url=https://drum.lib.umd.edu/handle/1903/11673 |publisher=UMD dissertation}}

After obtaining a PhD he taught at the U.S Military Academy, West Point, as an assistant professor from 2011 to 2014, his final military assignment.{{cite web |url=https://www.businessinsider.com/coming-home-this-west-point-grad-is-turning-ai-and-big-data-against-isis-and-gangs-2015-10|title=Coming Home: This West Point grad is using AI and Big Data for national security|website=Business Insider }} In 2014 he took a position as an assistant professor at Arizona State University. He earned his tenure at Arizona State and was promoted to Associate Professor in 2020.{{cite web |url=https://theconversation.com/profiles/paulo-shakarian-1189989|title = Paulo Shakarian Associate Professor at Arizona State University| date=December 21, 2020 }}

Since 2011 Shakarian has authored six books on subjects relating to his academic career - many of them focused on the intersection between AI, security, and data mining.{{Cite web|url=https://www.amazon.com/Paulo-Shakarian/e/B007LCWEDG|title=Books by Paulo Shakarian|last=|first=|date=|website=www.amazon.com|archive-url=|archive-date=|access-date=2019-08-07}}

In 2017, while maintaining his academic position he co-founded and led (as CEO) Cyber Reconnaissance, Inc., (CYR3CON), a business that specialized in combining artificial intelligence with information mined from malicious hacker communities to avoid cyber-attacks. The company raised $8 million in venture capital{{cite press release |url=https://www.businesswire.com/news/home/20200714005388/en/AI-Cyber-Attack-Prediction-Platform-CYR3CON-Secures-8.2-Million-Financing |title=AI Cyber Attack Prediction Platform CYR3CON Secures $8.2 Million Financing|date=July 14, 2020 }} and was acquired in 2022.{{cite web |url=https://www.bizjournals.com/albuquerque/inno/stories/news/2022/03/16/cyber-security-works-acquires-cyr3con.html | title= Albuquerque cybersecurity firm acquires Arizona machine learning startup}}

In June 2025, Shakarian announced that he had left his academic position at Arizona State to become the inaugural KG Tan Endowed Professor of Artificial Intelligence at Syracuse University.https://x.com/paulo_shak/status/1934689584451080573

In 2023, Shakarian's group released PyReason{{cite journal |last1=Aditya |first1=D. |title=PyReason: Software for Open World Temporal Logic |journal=AAAI-Make |date=2023 |arxiv=2302.13482 }} which is a modern implementation of annotated logic{{cite journal |last1=Kifer |first1=Michael |last2=Subrahmanian |first2=V.S. |title=Theory of generalized annotated logic programming and its applications |journal=Journal of Logic Programming |date=1992|doi=10.1016/0743-1066(92)90007-P }} with extensions to support temporal and open-world reasoning. PyReason was used in various collaborations with industry partners. This included work with SSCI where PyReason was used as a "semantic proxy" to replace a simulation for reinforcement learning{{cite journal |last1=Mukherji |first1=K. |last2=Parkar |first2=D. |last3=Pokala |first3=L. |last4=Aditya |first4=D. |last5=Shakarian |first5=P. |last6=Dorman |first6=C. |title=Scalable Semantic Non-Markovian Simulation Proxy for Reinforcement Learning |journal=IEEE Icsc |date=2024 |arxiv=2310.06835 }} where it provides a 1000x speedup over native simulation environments for agent policy training and provided transfer of PyReason-trained policies to simulation environments such as AFSIM and SC2. PyReason was also demonstrated as a method for robotic control in a joint ASU-SSCI demonstration.{{Cite web|url=https://www.youtube.com/watch?v=AHiSc0C_3mw|title=PyReason Sim-to-Real Demo|date=December 11, 2023|via=YouTube}} In a separate line of work, under the IARPA HAYSTAC program{{Cite web|url=https://www.iarpa.gov/research-programs/haystac|title=HAYSTAC|website=www.iarpa.gov}} PyReason was used in a strategy to generate movement trajectories using ideas from abductive inference.{{cite journal |last1=Bavikadi |first1=D. |display-authors=etal |title=Geospatial Trajectory Generation via Efficient Abduction: Deployment for Independent Testing |journal=40th Intl. Conference on Logic Programming (ICLP) |date=2024 |url=https://arxiv.org/html/2407.06447v1}} Here the authors leveraged properties of logic programming and A* search to generate movement trajectories that met certain criteria but resembled past agent activity.

=== Social Network Diffusion ===

In the 2012 paper “Large social networks can be targeted for viral marketing with small seed sets”,{{cite book |chapter-url=https://ieeexplore.ieee.org/document/6425793 |doi=10.1109/ASONAM.2012.11 |arxiv=1205.4431 |chapter=Large Social Networks Can be Targeted for Viral Marketing with Small Seed Sets |title=2012 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining |date=2012 |last1=Shakarian |first1=P. |last2=Paulo |first2=D. |pages=1–8 |isbn=978-1-4673-2497-7 }} Shakarian introduced a fast, novel method for identifying sets of nodes that can maximize the spread of a contagion in a social network based on the standard “tipping model.” The work was presented in a 2012 ASONAM paper (later extended in a 2013 journal SNAM{{Cite journal|url=https://link.springer.com/article/10.1007/s13278-013-0135-7|title=A scalable heuristic for viral marketing under the tipping model|first1=Paulo|last1=Shakarian|first2=Sean|last2=Eyre|first3=Damon|last3=Paulo|date=December 1, 2013|journal=Social Network Analysis and Mining|volume=3|issue=4|pages=1225–1248|via=Springer Link|doi=10.1007/s13278-013-0135-7|arxiv=1309.2963}} and described in a 2015 book published by Springer-Nature{{Cite book|url=https://link.springer.com/book/10.1007/978-3-319-23105-1|title=Diffusion in Social Networks|series=SpringerBriefs in Computer Science |date=2015 |via=link.springer.com|doi=10.1007/978-3-319-23105-1|isbn=978-3-319-23104-4 }} ). The concept was based around a graph decomposition designed to mimic the inverse of the diffusion process. The work was featured as part of MIT Technology Review’s “Best of 2013” and heralded as solving a “fundamental problem of viral marketing.”{{Cite web|url=https://www.technologyreview.com/2014/01/01/174746/best-of-2013-us-military-scientists-solve-the-fundamental-problem-of-viral-marketing/|title=Best of 2013: US Military Scientists Solve the Fundamental Problem of Viral Marketing|website=MIT Technology Review}}

In 2016, Shakarian’s team introduced a data mining framework in the paper “Darknet and deepnet mining for proactive cybersecurity threat intelligence” (Proc. IEE ISI 2016{{cite book |chapter-url=https://ieeexplore.ieee.org/document/7745435 |doi=10.1109/ISI.2016.7745435 |arxiv=1607.08583 |chapter=Darknet and deepnet mining for proactive cybersecurity threat intelligence |title=2016 IEEE Conference on Intelligence and Security Informatics (ISI) |date=2016 |last1=Nunes |first1=Eric |last2=Diab |first2=Ahmad |last3=Gunn |first3=Andrew |last4=Marin |first4=Ericsson |last5=Mishra |first5=Vineet |last6=Paliath |first6=Vivin |last7=Robertson |first7=John |last8=Shakarian |first8=Jana |last9=Thart |first9=Amanda |last10=Shakarian |first10=Paulo |pages=7–12 |isbn=978-1-5090-3865-7 }} and later described in a book published by Cambridge University press in 2017{{Cite book|url=https://www.cambridge.org/core/books/darkweb-cyber-threat-intelligence-mining/233E5624626A4EBEFD6DFFE25214D422|title=Darkweb Cyber Threat Intelligence Mining|first1=John|last1=Robertson|first2=Ahmad|last2=Diab|first3=Ericsson|last3=Marin|first4=Eric|last4=Nunes|first5=Vivin|last5=Paliath|first6=Jana|last6=Shakarian|first7=Paulo|last7=Shakarian|date=September 24, 2017|publisher=Cambridge University Press|doi=10.1017/9781316888513 |isbn=978-1-107-18577-7 }} ) which presented a framework for mining over 40 hacker websites – which not only demonstrated a scalable system for darkweb mining of hacker information, but also allowed for the ability to cross-examine cyber threat actors across multiple online forums – the study identified hundreds of hacker personas who participated in more than three different online marketplaces. The paper became one of the most cited papers of the history of the IEEE ISI conference and received media attention in Forbes{{Cite web|url=https://www.forbes.com/sites/kevinmurnane/2016/08/08/machine-learning-goes-dark-and-deep-to-find-zero-day-exploits-before-day-zero/|title=Machine Learning Goes Dark And Deep To Find Zero-Day Exploits Before Day Zero|first=Kevin|last=Murnane|website=Forbes}} and MIT Technology Review.{{Cite web|url=https://www.technologyreview.com/2016/08/05/107973/machine-learning-algorithm-combs-the-darknet-for-zero-day-exploits-and-finds-them/|title=Machine-Learning Algorithm Combs the Darknet for Zero Day Exploits, and Finds Them|website=MIT Technology Review}}

The following year, Shakarian and his team showed that data gathered from hacker communities on the dark web about specific software vulnerabilities often appeared before the use of zero-day exploits in a paper entitled “Proactive identification of exploits in the wild through vulnerability mentions online”.{{cite book |chapter-url=https://ieeexplore.ieee.org/document/8167501 |doi=10.1109/CYCONUS.2017.8167501 |chapter=Proactive identification of exploits in the wild through vulnerability mentions online |title=2017 International Conference on Cyber Conflict (CyCon U.S.) |date=2017 |last1=Almukaynizi |first1=Mohammed |last2=Nunes |first2=Eric |last3=Dharaiya |first3=Krishna |last4=Senguttuvan |first4=Manoj |last5=Shakarian |first5=Jana |last6=Shakarian |first6=Paulo |pages=82–88 |isbn=978-1-5386-2379-4 }}{{Cite web|url=https://scholar.google.com/scholar?hl=en&as_sdt=0,3&q=Proactive+identification+of+exploits+in+the+wild+through+vulnerability+mentions+online&btnG=|title=Google Scholar|website=scholar.google.com}} They found that this information could also be used to create features for machine learning approaches can successfully predict the use of exploits – even when accounting for temporal intermixing of data. The approach was enhanced with follow-on studies were the features were augmented using social network topology data (Proc. ACM CSS 2017{{Cite book|chapter-url=https://dl.acm.org/doi/10.1145/3145574.3145590|chapter=Predicting Cyber Threats through Hacker Social Networks in Darkweb and Deepweb Forums|first1=Mohammed|last1=Almukaynizi|first2=Alexander|last2=Grimm|first3=Eric|last3=Nunes|first4=Jana|last4=Shakarian|first5=Paulo|last5=Shakarian|title=Proceedings of the 2017 International Conference of the Computational Social Science Society of the Americas |date=October 19, 2017|publisher=Association for Computing Machinery|pages=1–7|via=ACM Digital Library|doi=10.1145/3145574.3145590|isbn=978-1-4503-5269-7 }} ) and the use of language models (Proc. AAAI 2018 {{Cite journal|url=https://ojs.aaai.org/index.php/AAAI/article/view/11428|title=DarkEmbed: Exploit Prediction with Neural Language Models|first1=Nazgol|last1=Tavabi|first2=Palash|last2=Goyal|first3=Mohammed|last3=Almukaynizi|first4=Paulo|last4=Shakarian|first5=Kristina|last5=Lerman|date=April 27, 2018|journal=Proceedings of the AAAI Conference on Artificial Intelligence|volume=32|issue=1|via=ojs.aaai.org|doi=10.1609/aaai.v32i1.11428}}).

• Neuro Symbolic Reasoning and Learning.{{cite book | url=https://link.springer.com/book/9783031391781 | title=Neuro Symbolic Reasoning and Learning }}
• Introduction to Cyber-Warfare: A Multidisciplinary Approach.
• Diffusion in Social Networks (SpringerBriefs in Computer Science).
• Darkweb Cyber Threat Intelligence Mining.
• Artificial Intelligence Tools for Cyber Attribution (SpringerBriefs in Computer Science).
• Cyber Warfare: Building the Scientific Foundation (Advances in Information Security).
• Geospatial Abduction: Principles and Practice.

{{reflist}}

• [https://www.researchgate.net/profile/Paulo_Shakarian/publications Research Gate Profile]
• [https://scholar.google.com/citations?user=OUAMn6oAAAAJ&hl=en Google Scholar Citations]
• [https://dblp.org/pers/hd/s/Shakarian:Paulo Computer Science Bibliography]
• [https://isearch.asu.edu/profile/2424157 Academic Profile, Arizona State University]
• [https://www.cyr3con.ai/ CYR3CON website]

{{Portal bar|United States|Biography}}

{{DEFAULTSORT:Shakarian, Paulo}}

Category:American chief executives

Category:Living people

Category:Year of birth missing (living people)