Signal jamming defense not up to the task? These researchers have a solution
Mon 09.18.23 / Zorain Nizamani
Signal jamming defense not up to the task? These researchers have a solution
Mon 09.18.23 / Zorain Nizamani
Mon 09.18.23 / Zorain Nizamani
Mon 09.18.23 / Zorain Nizamani
Signal jamming defense not up to the task? These researchers have a solution
Mon 09.18.23 / Zorain Nizamani
Signal jamming defense not up to the task? These researchers have a solution
Mon 09.18.23 / Zorain Nizamani
Mon 09.18.23 / Zorain Nizamani
Mon 09.18.23 / Zorain Nizamani
Hai Nguyen (left) and Guevara Noubir.
In today’s fast-paced world, high-speed internet and mobile service have become far more of a necessity than a luxury. But as evolving and maturing data services demand higher internet speeds, and as operating systems beg protection, hackers and hostiles continue to interfere. For some, this involves hacking home and office wireless connections with the aim of extracting personal or business data.
But whether their targets are government-run institutions, private companies, or individual users, these attackers often employ high-powered signal jamming apparatuses — wireless portable devices that hinder communication between devices. For users seeking to evade these attacks, such jammers are also the defense.
Keeping this dichotomy in mind, former Khoury doctoral student Hai Nguyen and his advisor Guevara Noubir, both members of Khoury College’s Cybersecurity and Privacy Institute, have pioneered a novel approach that essentially cancels these high-powered jammers in situations where traditional techniques fail. This failure can happen because the traditional techniques are designed for nonmalicious interference, require mechanically moving parts that react slowly to jamming, or require additional bands of radio frequency to achieve resilience. The duo’s technique, which circumvents these scenarios, is called JaX.
“When you have wireless communication, you want to make it as robust and reliable as possible. As researchers, we like to tackle hard problems, and this problem has always been around,” Noubir said. “We wanted to solve it with a unique angle, and that angle was to develop safe communication techniques for GPS and Wi-Fi.”
READ: GPS is critical to modern life. It’s also vulnerable, and this researcher is out to fix that.
Nguyen and Noubir began working on this machine-learning-driven idea about a year ago, just as the Russia–Ukraine war — where signal jamming has played a massive role — was ramping up. As they built a large set of synthetic data and collected experimental material, their goal was to build a kind of black box which could be placed in front of a network and seamlessly protect users. The solution simplifies the cancelling of high-powered signal jammers by not requiring complex machinery.
“For data collection we built a test bed, for the transmitter we used software radio, and for the jammer and receiver we used other radios,” Noubir explained. “We sent legitimate signals and then we also sent the interference. We received them on two antennas which stored the data, so we knew what we were sending and what was interfering.
“One of the cool things about our results,” he added, “was that we could have an adversary jammer transmit signals more powerful than the legitimate ones, and we could remove the interference like it never existed!”
Noubir believes that the findings of the paper could prove useful for a wide range of individual and organizational users looking to avoid malicious attacks on their data.
“The fact that it is possible to achieve a really low bit error rate shows that we can overcome an adversary who is transmitting at one hundred times more than the legitimate signals,” he stated. “You can have something extremely noisy in the environment, but because we have JaX, we can estimate what the jammer is really transmitting, subtract it, and leave only the legitimate signals.”
While the process sounds promising, the benefits would only matter if the technology were logistically sound and affordable — two barriers that often prevent innovative technology from becoming ubiquitous. But Noubir believes he and Nguyen have cleared that hurdle too.
“Our machine learning models are compact, so if you are designing any new systems, you can easily incorporate this,” he said. “Similarly, if the Department of Defense wanted to integrate JaX, compared to other models, this price for this would be negligible and the model would be more efficient.”
Noubir and Nguyen — who recently defended his thesis and joined Meta as a research scientist — acknowledge that newer approaches to older problems would always require tweaks and fixes. Nonetheless, they’re hopeful that JaX might be the solution to a longstanding network issue, and they’re hoping to bring it to market.
Hai Nguyen (left) and Guevara Noubir.
In today’s fast-paced world, high-speed internet and mobile service have become far more of a necessity than a luxury. But as evolving and maturing data services demand higher internet speeds, and as operating systems beg protection, hackers and hostiles continue to interfere. For some, this involves hacking home and office wireless connections with the aim of extracting personal or business data.
But whether their targets are government-run institutions, private companies, or individual users, these attackers often employ high-powered signal jamming apparatuses — wireless portable devices that hinder communication between devices. For users seeking to evade these attacks, such jammers are also the defense.
Keeping this dichotomy in mind, former Khoury doctoral student Hai Nguyen and his advisor Guevara Noubir, both members of Khoury College’s Cybersecurity and Privacy Institute, have pioneered a novel approach that essentially cancels these high-powered jammers in situations where traditional techniques fail. This failure can happen because the traditional techniques are designed for nonmalicious interference, require mechanically moving parts that react slowly to jamming, or require additional bands of radio frequency to achieve resilience. The duo’s technique, which circumvents these scenarios, is called JaX.
“When you have wireless communication, you want to make it as robust and reliable as possible. As researchers, we like to tackle hard problems, and this problem has always been around,” Noubir said. “We wanted to solve it with a unique angle, and that angle was to develop safe communication techniques for GPS and Wi-Fi.”
READ: GPS is critical to modern life. It’s also vulnerable, and this researcher is out to fix that.
Nguyen and Noubir began working on this machine-learning-driven idea about a year ago, just as the Russia–Ukraine war — where signal jamming has played a massive role — was ramping up. As they built a large set of synthetic data and collected experimental material, their goal was to build a kind of black box which could be placed in front of a network and seamlessly protect users. The solution simplifies the cancelling of high-powered signal jammers by not requiring complex machinery.
“For data collection we built a test bed, for the transmitter we used software radio, and for the jammer and receiver we used other radios,” Noubir explained. “We sent legitimate signals and then we also sent the interference. We received them on two antennas which stored the data, so we knew what we were sending and what was interfering.
“One of the cool things about our results,” he added, “was that we could have an adversary jammer transmit signals more powerful than the legitimate ones, and we could remove the interference like it never existed!”
Noubir believes that the findings of the paper could prove useful for a wide range of individual and organizational users looking to avoid malicious attacks on their data.
“The fact that it is possible to achieve a really low bit error rate shows that we can overcome an adversary who is transmitting at one hundred times more than the legitimate signals,” he stated. “You can have something extremely noisy in the environment, but because we have JaX, we can estimate what the jammer is really transmitting, subtract it, and leave only the legitimate signals.”
While the process sounds promising, the benefits would only matter if the technology were logistically sound and affordable — two barriers that often prevent innovative technology from becoming ubiquitous. But Noubir believes he and Nguyen have cleared that hurdle too.
“Our machine learning models are compact, so if you are designing any new systems, you can easily incorporate this,” he said. “Similarly, if the Department of Defense wanted to integrate JaX, compared to other models, this price for this would be negligible and the model would be more efficient.”
Noubir and Nguyen — who recently defended his thesis and joined Meta as a research scientist — acknowledge that newer approaches to older problems would always require tweaks and fixes. Nonetheless, they’re hopeful that JaX might be the solution to a longstanding network issue, and they’re hoping to bring it to market.
Hai Nguyen (left) and Guevara Noubir.
In today’s fast-paced world, high-speed internet and mobile service have become far more of a necessity than a luxury. But as evolving and maturing data services demand higher internet speeds, and as operating systems beg protection, hackers and hostiles continue to interfere. For some, this involves hacking home and office wireless connections with the aim of extracting personal or business data.
But whether their targets are government-run institutions, private companies, or individual users, these attackers often employ high-powered signal jamming apparatuses — wireless portable devices that hinder communication between devices. For users seeking to evade these attacks, such jammers are also the defense.
Keeping this dichotomy in mind, former Khoury doctoral student Hai Nguyen and his advisor Guevara Noubir, both members of Khoury College’s Cybersecurity and Privacy Institute, have pioneered a novel approach that essentially cancels these high-powered jammers in situations where traditional techniques fail. This failure can happen because the traditional techniques are designed for nonmalicious interference, require mechanically moving parts that react slowly to jamming, or require additional bands of radio frequency to achieve resilience. The duo’s technique, which circumvents these scenarios, is called JaX.
“When you have wireless communication, you want to make it as robust and reliable as possible. As researchers, we like to tackle hard problems, and this problem has always been around,” Noubir said. “We wanted to solve it with a unique angle, and that angle was to develop safe communication techniques for GPS and Wi-Fi.”
READ: GPS is critical to modern life. It’s also vulnerable, and this researcher is out to fix that.
Nguyen and Noubir began working on this machine-learning-driven idea about a year ago, just as the Russia–Ukraine war — where signal jamming has played a massive role — was ramping up. As they built a large set of synthetic data and collected experimental material, their goal was to build a kind of black box which could be placed in front of a network and seamlessly protect users. The solution simplifies the cancelling of high-powered signal jammers by not requiring complex machinery.
“For data collection we built a test bed, for the transmitter we used software radio, and for the jammer and receiver we used other radios,” Noubir explained. “We sent legitimate signals and then we also sent the interference. We received them on two antennas which stored the data, so we knew what we were sending and what was interfering.
“One of the cool things about our results,” he added, “was that we could have an adversary jammer transmit signals more powerful than the legitimate ones, and we could remove the interference like it never existed!”
Noubir believes that the findings of the paper could prove useful for a wide range of individual and organizational users looking to avoid malicious attacks on their data.
“The fact that it is possible to achieve a really low bit error rate shows that we can overcome an adversary who is transmitting at one hundred times more than the legitimate signals,” he stated. “You can have something extremely noisy in the environment, but because we have JaX, we can estimate what the jammer is really transmitting, subtract it, and leave only the legitimate signals.”
While the process sounds promising, the benefits would only matter if the technology were logistically sound and affordable — two barriers that often prevent innovative technology from becoming ubiquitous. But Noubir believes he and Nguyen have cleared that hurdle too.
“Our machine learning models are compact, so if you are designing any new systems, you can easily incorporate this,” he said. “Similarly, if the Department of Defense wanted to integrate JaX, compared to other models, this price for this would be negligible and the model would be more efficient.”
Noubir and Nguyen — who recently defended his thesis and joined Meta as a research scientist — acknowledge that newer approaches to older problems would always require tweaks and fixes. Nonetheless, they’re hopeful that JaX might be the solution to a longstanding network issue, and they’re hoping to bring it to market.
Hai Nguyen (left) and Guevara Noubir.
In today’s fast-paced world, high-speed internet and mobile service have become far more of a necessity than a luxury. But as evolving and maturing data services demand higher internet speeds, and as operating systems beg protection, hackers and hostiles continue to interfere. For some, this involves hacking home and office wireless connections with the aim of extracting personal or business data.
But whether their targets are government-run institutions, private companies, or individual users, these attackers often employ high-powered signal jamming apparatuses — wireless portable devices that hinder communication between devices. For users seeking to evade these attacks, such jammers are also the defense.
Keeping this dichotomy in mind, former Khoury doctoral student Hai Nguyen and his advisor Guevara Noubir, both members of Khoury College’s Cybersecurity and Privacy Institute, have pioneered a novel approach that essentially cancels these high-powered jammers in situations where traditional techniques fail. This failure can happen because the traditional techniques are designed for nonmalicious interference, require mechanically moving parts that react slowly to jamming, or require additional bands of radio frequency to achieve resilience. The duo’s technique, which circumvents these scenarios, is called JaX.
“When you have wireless communication, you want to make it as robust and reliable as possible. As researchers, we like to tackle hard problems, and this problem has always been around,” Noubir said. “We wanted to solve it with a unique angle, and that angle was to develop safe communication techniques for GPS and Wi-Fi.”
READ: GPS is critical to modern life. It’s also vulnerable, and this researcher is out to fix that.
Nguyen and Noubir began working on this machine-learning-driven idea about a year ago, just as the Russia–Ukraine war — where signal jamming has played a massive role — was ramping up. As they built a large set of synthetic data and collected experimental material, their goal was to build a kind of black box which could be placed in front of a network and seamlessly protect users. The solution simplifies the cancelling of high-powered signal jammers by not requiring complex machinery.
“For data collection we built a test bed, for the transmitter we used software radio, and for the jammer and receiver we used other radios,” Noubir explained. “We sent legitimate signals and then we also sent the interference. We received them on two antennas which stored the data, so we knew what we were sending and what was interfering.
“One of the cool things about our results,” he added, “was that we could have an adversary jammer transmit signals more powerful than the legitimate ones, and we could remove the interference like it never existed!”
Noubir believes that the findings of the paper could prove useful for a wide range of individual and organizational users looking to avoid malicious attacks on their data.
“The fact that it is possible to achieve a really low bit error rate shows that we can overcome an adversary who is transmitting at one hundred times more than the legitimate signals,” he stated. “You can have something extremely noisy in the environment, but because we have JaX, we can estimate what the jammer is really transmitting, subtract it, and leave only the legitimate signals.”
While the process sounds promising, the benefits would only matter if the technology were logistically sound and affordable — two barriers that often prevent innovative technology from becoming ubiquitous. But Noubir believes he and Nguyen have cleared that hurdle too.
“Our machine learning models are compact, so if you are designing any new systems, you can easily incorporate this,” he said. “Similarly, if the Department of Defense wanted to integrate JaX, compared to other models, this price for this would be negligible and the model would be more efficient.”
Noubir and Nguyen — who recently defended his thesis and joined Meta as a research scientist — acknowledge that newer approaches to older problems would always require tweaks and fixes. Nonetheless, they’re hopeful that JaX might be the solution to a longstanding network issue, and they’re hoping to bring it to market.
Khoury Social
Contact Khoury
Khoury Social
Contact Khoury
Khoury Social
Contact Khoury
Khoury Social
Contact Khoury