Weaponized Disinformation Poses Serious Threat to Urban Transit Systems

Media Releases

Weaponized Disinformation Poses Serious Threat to Urban Transit Systems

posted

Share

Copy Link Facebook Linkedin X Email

Hoboken, N.J., January 6, 2025 - As every straphanger knows, public transit systems are fantastic-except when they aren't. A single station closure can ruin a commuter's morning, and even minor delays or disruptions can snowball into major problems as thousands of passengers rush to find alternate routes, straining other parts of the transit network.

In a study published this month in Reliability Engineering and System Safety, researchers from Stevens Institute of Technology and the University of Oklahoma warn that the complexity and fragility of urban transit networks could be exploited by terrorists or other bad actors. Using AI models, the team shows how low-cost attacks based on the spread of misinformation could significantly disrupt transit networks, causing widespread chaos and economic harm.

"This study reveals serious vulnerabilities that could be targeted relatively easily to disrupt urban transit systems," says Dr. Jose Ramirez-Marquez, a professor in Stevens' Department of Systems and Enterprises. "The purposeful spread of misinformation-such as bomb threats or other bogus reports-has the potential to cause serious problems for the world's public transport networks."

To test transit systems' resilience to disinformation, the team used AI models to study the Port Authority Trans-Hudson (PATH) system in New Jersey and New York, which is relied on by more than 200,000 daily riders. Based on social media alerts published by PATH, the team used AI and natural language processing (NLP) tools to categorize disruption scenarios, from service delays to security incidents, many of which could be triggered or exacerbated by the spread of misinformation.

Next, the team used computer modeling and real-world ridership data to test how the PATH network would respond to disinformation regarding various disruption scenarios. That meant quantifying the direct impact of any given disruption-such as a train being held on a platform, or a station being temporarily closed-but also modeling passengers' likely responses, and the ways in which delays would subsequently cascade through the network as a whole.

"A disruption might be caused by a single false report of an unattended suitcase or a rowdy passenger on a train-but we've shown how that single bit of disinformation can ripple out to degrade performance across the PATH network," Dr. Ramirez-Marquez explains.

The results were striking: a single brief station closure was found to cause cumulative delays of up to 16,441 minutes for impacted passengers. It also imposed additional costs averaging up to $18.13 per passenger as riders were forced to pay for taxis, buses, and other alternate transportation.

Even relatively low levels of disinformation could lead to major PATH hubs such as its Newark or World Trade Center stations experiencing forced closures. Higher levels of disinformation, perhaps timed to coincide with major sporting events for maximum disruption, could lead to stations being closed as much as 11% of the time, triggering delays and economic impacts across the New York and New Jersey region.

Modeling such impacts is valuable because it can help network administrators prepare for and respond to disinformation, Dr. Ramirez-Marquez says. "Something as simple as quickly checking whether a report is true-such as walking down a platform and looking for an abandoned suitcase, or confirming that a security incident is actually happening-can mitigate many of these impacts," he explains. "But to implement that at scale, you need to have anticipated and planned for the scenarios in question."

The Stevens team now hopes to extend its work to model potential disruptions across entire urban areas, and show how social media chatter-including misinformation-can be used to anticipate and respond to disruptions in real time. "Right now, most cities are reactive: they send first responders out when something bad happens," Dr. Ramirez-Marquez says. "With the right AI tools, cities could spot problems before they happen-reducing their vulnerability to weaponized misinformation, and minimizing disruption for everyone."

About Stevens Institute of Technology
Stevens Institute of Technology is a premier, private research university situated in Hoboken, New Jersey. Since our founding in 1870, technological innovation has been the hallmark of Stevens' education and research. Within the university's three schools and one college, more than 8,000 undergraduate and graduate students collaborate closely with faculty in an interdisciplinary, student-centric, entrepreneurial environment. Academic and research programs spanning business, computing, engineering, the arts and other disciplines actively advance the frontiers of science and leverage technology to confront our most pressing global challenges. The university continues to be consistently ranked among the nation's leaders in career services, post-graduation salaries of alumni and return on tuition investment.

Stevens Media Contact
Kara Panzer
Director of Public and Media Relations
Division of University Relations
845-475-4594
[email protected]

View all media releases