Strahinja (Strajo) Janjusevic, a second-year master’s student at the Massachusetts Institute of Technology (MIT), is making waves in the field of cybersecurity, particularly focusing on the maritime industry. Originally from Montenegro, Janjusevic has leveraged a unique educational opportunity offered by a program that allows selected students from allied nations to attend the U.S. Naval Academy. There, he earned dual bachelor’s degrees in cyber operations and computer science, providing him with a solid foundation in the cybersecurity landscape.
Pursuing further knowledge in artificial intelligence and cybersecurity, Janjusevic enrolled in the Technology and Policy Program (TPP) at MIT’s Institute for Data, Systems, and Society (IDSS). His current research aims to enhance the cybersecurity of critical maritime infrastructure by integrating AI techniques, examining the technology’s implications alongside necessary policy frameworks. “My current research focuses on applying AI techniques to cybersecurity problems and examining the policy implications of these advancements, especially in the context of maritime cybersecurity,” said Janjusevic.
His academic journey has allowed him to collaborate with significant entities like the U.S. military and the National Security Agency, intensifying his interest in complex cybersecurity challenges. During his undergraduate studies, he interned with major organizations, including Microsoft and NASA, where he developed tools for cloud incident response and visualized solar data, respectively. This practical experience laid the groundwork for his current endeavors at MIT, where he appreciates the diverse research domains and collaborative environment of the TPP program.
Janjusevic’s thesis integrates concepts from cybersecurity, AI, deep learning, and control theory, focusing specifically on securing large legacy ships against cyber threats. Such vulnerabilities can pose severe risks to national security, not to mention economic repercussions. “Strajo is working to outsmart maritime GPS spoofing,” noted Saurabh Amin, the Edmund K. Turner Professor in Civil Engineering. “Such attacks have already lured vessels off course in contested waters. His approach layers physics-based trajectory models with deep learning, catching threats that no single method can detect alone.”
The research employs advanced threat modeling and vessel dynamics to train AI systems to differentiate between legitimate maneuvers and spoofed signals. Utilizing a hybrid framework that includes an internal long short-term memory (LSTM) autoencoder, Janjusevic’s work analyzes signal integrity while predicting vessel movements based on environmental factors. By comparing these predictions against actual GPS positions, the system effectively distinguishes between sensor noise and malicious spoofing attacks, enhancing human operators’ decision-making capabilities.
In summer 2025, Janjusevic interned with Vectra AI’s Network Detection team, where he investigated emerging threats posed by AI technologies. His research on the model context protocol (MCP) highlighted how this standard could be exploited for autonomous hacking operations. The findings were recently presented in the preprint, “Hiding in the AI Traffic: Abusing MCP for LLM-Powered Agentic Red Teaming.” “I was able to gain practical insights and hands-on experience into how a data science team uses AI models to detect anomalies in a network,” he commented, noting that this experience significantly informed his academic research.
Janjusevic’s contributions extend beyond academics. He is actively involved in the MIT Maritime Consortium, a collaboration that connects academia, industry, and regulatory agencies to tackle maritime cybersecurity challenges. This initiative includes international cooperation with partners from countries like Singapore and South Korea. “In AI cybersecurity, the policy element is really important, as the field is so fast-moving and the consequences of hacking can be so dangerous,” he emphasized.
Looking ahead, Janjusevic is helping organize two major conferences: the Harvard European Conference in February, which will gather global officials and diplomats, and the Technology and National Security Conference in April, a joint effort between Harvard and MIT focused on pressing national security challenges. “I’m striving to find a position where I can influence and advance the cybersecurity field with AI, while at the same time leading collaboration and innovation between the United States and Montenegro,” he said. His goal is to serve as a bridge between Europe and the U.S. in matters of national security, AI, and cybersecurity, leveraging his unique background and insights.
See also
Anthropic’s Claims of AI-Driven Cyberattacks Raise Industry Skepticism
Anthropic Reports AI-Driven Cyberattack Linked to Chinese Espionage
Quantum Computing Threatens Current Cryptography, Experts Seek Solutions
Anthropic’s Claude AI exploited in significant cyber-espionage operation
AI Poisoning Attacks Surge 40%: Businesses Face Growing Cybersecurity Risks
