Taqi Raza
Assistant Professor of Electrical and Computer Engineering University of Massachusetts Amherst
- Amherst MA
Taqi Raza is an expert in developing secure and reliable solutions for emerging digital ecosystems.
University of Massachusetts Amherst
View more experts managed by University of Massachusetts Amherst
Expertise
Biography
Social Media
Video
Education
University of California Los Angeles
Ph.D.
Computer Science
2019
University of California Los Angeles
M.S.
Computer Science
2017
Ajou University, South Korea
M.Eng.
Information and Communication Engineering
2008
National University of Sciences and Technology, Pakistan
B.S.
Information Technology
2006
Select Recent Media Coverage
Digital wallet loophole: What you need to know
FOX 26 Houston tv
2025-08-27
Researchers say they have discovered a loophole that can let thieves use a credit card in a digital wallet even after it's been reported stolen.
Cybersecurity Alert: Why Your Mobile Wallet May Not Be Safe Even With a VPN
Investopedia online
2025-07-05
"Every bank or financial institution has a different authentication method," explains Taqi Raza, an assistant professor at UMass Amherst and one of the researchers on the cybersecurity team.
What Google’s quantum computing breakthrough Willow means for the future of bitcoin and other cryptos
CNBC online
2024-12-22
Taqi Raza, assistant professor of electrical and computer engineering at the University of Massachusetts Amherst, said existing cryptos will have to evolve to ward off qubits. “As the potential for quantum computers to break existing cryptography becomes more of a concern, new cryptocurrencies specifically designed to be quantum-safe could be developed. These new quantum cryptos would integrate PQC, cryptographic algorithms that are resistant to the computational power of quantum computers,” Raza said.
Digital security expert shares advice on keeping your personal information safe when using digital wallets
Spectrum News 1 online
2024-12-02
Taqi Raza recently uncovered a vulnerability in digital security systems like Apple Pay and Google Pay. He said while companies say the wallets are secure, there is a loophole attackers can use and bypass security checks enforced by banks.
New Study Reveals Loophole in Digital Wallet Security
UMass News Office online
2024-08-14
“What we have discovered is [that] these digital wallets are not secure,” says Taqi Raza, assistant professor of electrical and computer engineering and an author on the paper. “The main reason is that they have unconditional trust between the cardholder, the wallet and the bank.”
UMass Amherst Researchers Join $26 Million Quantum Computing Effort to Build Internet of the Future
UMass News Office online
2024-03-18
Towsley and his UMass colleagues, including Krastanov and Filip Rozpedek, assistant professor of information and computer science, as well as Taqi Raza, assistant professor of electrical and computer engineering in the College of Engineering, are working out how to send qubits without the risk of their loss or decay in a secure way. It’s a problem that requires expertise in both computer science and engineering, because, as Raza, whose expertise is in the security of critical infrastructures, puts it, “security cuts across all the various specialties that must contribute to a successful quantum network. We are working to embed security principles in quantum networks from the start.”
Select Publications
InferNet: Exploiting Aggregate GPU Profiles as Side-Channel for DNN Architecture Inference
ACM Transactions on AI Security and Privacy2026
Deep Neural Networks (DNNs) have become ubiquitous for their ability to solve problems across various domains, including computer vision, natural language processing, and speech recognition. However, as their adoption grows, they face a range of security threats, such as model stealing, architecture extraction, and manipulation, which can compromise their integrity, privacy, and functionality.
Scrutinizing security in industrial control systems: An architectural vulnerabilities and communication network perspective
IEEE Access2024
Technological advancement plays a crucial role in our daily lives and constantly transforms the industrial sector. However, these technologies also introduce new security vulnerabilities to Industrial Control Systems (ICS). Attackers take advantage of these weaknesses to infiltrate the ICS environment. The size of the targeted industry and the attacker’s knowledge of the internal ICS environment are crucial factors in determining the degree of impact.
SREFBN: Enhanced feature block network for single‐image super‐resolution
IET Image Processing2022
Deep learning has assisted the field of single‐image super‐resolution (SR) in achieving new heights. However, the task of restoring a high‐resolution (HR) image from a highly degraded low‐resolution (LR) image is sophisticated due to poor image restoration quality. A novel and effective lightweight SR method is presented as super‐resolution via an enhanced feature block network (SREFBN) that successfully reconstructs an HR image using a corresponding LR image with a purposed deep residual block.
A comprehensive study on cyber attacks in communication networks in water purification and distribution plants: challenges, vulnerabilities, and future prospects
Sensors2023
In recent years, the Internet of Things (IoT) has had a big impact on both industry and academia. Its profound impact is particularly felt in the industrial sector, where the Industrial Internet of Things (IIoT), also known as Industry 4.0, is revolutionizing manufacturing and production through the fusion of cutting-edge technologies and network-embedded sensing devices. The IIoT revolutionizes several industries, including crucial ones such as oil and gas, water purification and distribution, energy, and chemicals, by integrating information technology (IT) with industrial control and automation systems.
Binary black-box evasion attacks against deep learning-based static malware detectors with adversarial byte-level language model
arXiv preprint2020
Anti-malware engines are the first line of defense against malicious software. While widely used, feature engineering-based anti-malware engines are vulnerable to unseen (zero-day) attacks. Recently, deep learning-based static anti-malware detectors have achieved success in identifying unseen attacks without requiring feature engineering and dynamic analysis. However, these detectors are susceptible to malware variants with slight perturbations, known as adversarial examples.
