Initially from the small Balkan nation of Montenegro, Strahinja (Strajo) Janjusevic says his life has unfolded in sudden methods, for which he’s deeply grateful. After graduating from highschool, he was chosen to symbolize his nation in the USA, learning cyber operations and laptop science on the U.S. Naval Academy in Annapolis, Maryland. He has since continued his cybersecurity research and is at present a second-year grasp’s pupil within the Know-how and Coverage Program (TPP), hosted by the MIT Institute for Information, Programs, and Society (IDSS). His analysis with the MIT Laboratory for Info and Resolution Programs (LIDS) and the MIT Maritime Consortium staff goals to enhance the cybersecurity of vital maritime infrastructure utilizing synthetic intelligence, contemplating each the expertise and coverage frameworks of options.
“My present analysis focuses on making use of AI strategies to cybersecurity issues and inspecting the coverage implications of those developments, particularly within the context of maritime cybersecurity,” says Janjusevic. “Representing my nation on the highest ranges of training and business has given me a singular perspective on cybersecurity challenges.”
Janjusevic’s pathway from Montenegro to Maryland was created by a program that enables chosen college students from allied international locations to attend the U.S. Naval Academy. Janjusevic graduated with a twin bachelor’s diploma in cyber operations and laptop science. His undergraduate expertise supplied alternatives to collaborate with the U.S. navy and the Nationwide Safety Company, exposing him to high-level cybersecurity operations and fueling his curiosity in tackling complicated cybersecurity challenges. Throughout his undergraduate research, he additionally interned with Microsoft, growing instruments for cloud incident response, and with NASA, visualizing photo voltaic information for analysis purposes.
Following his commencement, he realized that he nonetheless wanted extra information, significantly within the space of AI and cybersecurity. TPP appealed to him instantly due to its twin emphasis on rigorous engineering innovation and the coverage evaluation wanted to deploy it successfully. Janjusevic’s experiences at TPP have been an enormous change from his time on the U.S. Naval Academy, with a distinct tempo and setting. He has particularly appreciated having the ability to broaden his understanding about a wide range of analysis domains and apply the self-discipline and information he earned throughout his time on the academy.
“My TPP expertise has been wonderful,” says Janjusevic. “The cohort is admittedly small, so it appears like a household, and everyone seems to be engaged on various, high-impact issues.”
Mitigating the dangers of rising applied sciences
Janjusevic’s thesis brings collectively disciplines of cybersecurity, AI and deep studying, and management principle and physics, specializing in securing maritime cyber-physical methods — specifically, giant legacy ships. The hacking of those ships’ networks can lead to substantial injury to nationwide safety, in addition to severe financial results.
“Strajo is working to outsmart maritime GPS spoofing,” says Saurabh Amin, the Edmund Okay. Turner Professor in Civil Engineering. “Such assaults have already lured vessels off target in contested waters. His strategy layers physics-based trajectory fashions with deep studying, catching threats that no single methodology can detect alone. His experience has been very useful in advancing our work on menace modeling and assault detection.”
The analysis makes use of superior menace modeling and vessel dynamics to coach AI methods to tell apart between reliable maneuvers and spoofed alerts. It includes constructing a framework that employs an inner LSTM (lengthy short-term reminiscence) autoencoder to research sign integrity, whereas concurrently utilizing a physics-based forecaster to foretell the vessel’s motion based mostly on environmental components like wind and the ocean state. By evaluating these predictions towards reported GPS positions, the system can successfully distinguish between pure sensor noise and malicious spoofing assaults. This hybrid framework is designed to empower, not exchange, human operators, offering verified navigation information that enables watch standers to tell apart technical glitches from strategic cyberattacks.
Janjusevic has been in a position to improve his tutorial analysis with business expertise. In summer time 2025, he interned with the Community Detection staff on the AI cybersecurity firm Vectra AI. There, he investigated potential threats new applied sciences can convey, significantly AI brokers and the mannequin context protocol (MCP) — the rising commonplace for AI agent communication. His analysis demonstrated how this expertise could possibly be repurposed for autonomous hacking operations and superior command and management. This work on the safety dangers of agentic AI was not too long ago introduced within the preprint, “Hiding within the AI Site visitors: Abusing MCP for LLM-Powered Agentic Pink Teaming.”
“I used to be in a position to acquire sensible insights and hands-on expertise into how a knowledge science staff makes use of AI fashions to detect anomalies in a community,” says Janjusevic. “This work inside business instantly knowledgeable the anomaly detection fashions in my analysis.”
Worldwide coverage perspective
“Strajo brings not only a excessive degree of intelligence and vitality to his work on cyber-physical safety for service provider vessels, but additionally a powerful intuition from his Navy coaching that resonates deeply with the analysis effort and grounds it in actionable coverage,” says Fotini Christia, the Ford Worldwide Professor of the Social Sciences, director of IDSS and the MIT Sociotechnical Programs Analysis Middle, and a frontrunner of the MIT Maritime Consortium.
Janjusevic participates within the cybersecurity efforts of the Maritime Consortium, a collaboration between academia, business, and regulatory businesses centered on growing technological options, business requirements, and insurance policies. The consortium consists of cooperation with some worldwide members, together with from Singapore and South Korea.
“In AI cybersecurity, the coverage factor is admittedly essential, as the sphere is so fast-moving and the results of hacking will be so harmful,” says Janjusevic. “I feel there’s nonetheless lots of want for coverage work on this area.”
Janjusevic can be at present serving to to prepare two upcoming main conferences: the Harvard European Convention in February, which can convene officers and diplomats from throughout the globe, and the Know-how and Nationwide Safety Convention in April, a collaboration of Harvard and MIT that brings collectively prime leaders from authorities, business, and academia to deal with vital challenges in nationwide safety.
“I’m striving to discover a place the place I can affect and advance the cybersecurity subject with AI, whereas on the similar time main collaboration and innovation between the USA and Montenegro,” says Janjusevic. “My objective is to be a bridge between Europe and the U.S. on this area of nationwide safety, AI, and cybersecurity, bringing my information to each side.”
