We are pleased to share that two research papers from the Syed Babar Ali School of Science and Engineering (SBASSE), LUMS, have been accepted for presentation at the 28th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2025).

MICCAI 2025 will take place from September 23–27, 2025, at the Daejeon Convention Center in South Korea, a city celebrated as the “Silicon Valley of Korea” and a hub for science and innovation. MICCAI is widely regarded as a leading global platform in the domains of medical image computing and AI-assisted healthcare technologies. Ranked ‘A’ by the CORE conference rankings, this year’s conference received a record 3,677 submissions, which is 28% more than last year. Of these, 3,447 papers underwent peer review, with only 1,014 accepted, reflecting a highly competitive 29% acceptance rate.

Both accepted papers were developed as part of MS thesis projects under the supervision of Dr. Murtaza Taj, Associate Professor in the Department of Computer Science at SBASSE, LUMS. The work highlights SBASSE’s continued emphasis on mentorship, interdisciplinary collaboration, and impactful research in emerging areas of science and technology.

1. CATVis: Context-Aware Thought Visualization
This paper investigates how the cognitive process of interpreting medical images can be visualized, offering new possibilities for training and diagnostic support in clinical environments.

Authors: Hamza Ahmad (Undergrad. – FCCU, Founding AI Eng. – Uplift AI), Tariq Mehmood (MSCS, LUMS), Dr. Muhammad Haroon Shakeel (Arbisoft, PhD LUMS), Dr. Murtaza Taj (LUMS)
Hamza and Tariq contributed equally to this research.

2. Localization Lens for Improving Medical Vision-Language Models
The second study introduces a localization-based framework to enhance the performance and interpretability of AI models that combine visual and textual data in medical imaging.

 

Authors: Hasan Farooq (MSCS, LUMS), Dr. Murtaza Taj (LUMS), Dr. Mehwish Nasim (University of Western Australia), Dr. Arif Mehmood (ITU)

These recognitions are a testament to the quality of research training at SBASSE, and the global relevance of the scientific questions explored by its students and faculty.
Congratulations to all authors and collaborators on this remarkable achievement.
 

Dr. Maryam Mustafa, Assistant Professor at the Department of Computer Science, Co-founder Awaaz-e-Sehat and Director of the Saida Waheed Gender Initiative at LUMS, has been featured by the Bill & Melinda Gates Foundation for her work in digital health, particularly her efforts to support maternal care through contextually relevant technology.

The feature highlights Awaaz-e-Sehat, an AI-powered, voice-enabled record management and diagnostic support system developed to assist frontline health workers in Pakistan. The system is designed to make digital tools more accessible in settings with limited literacy and infrastructure, allowing community health providers to record and retrieve patient data using voice input in local languages. The system also supports health care workers by providing diagnostic support so patients receive timely interventions and care.

Dr. Maryam and her team have worked closely with public health experts and community partners to co-design the platform, ensuring that the technology aligns with on-the-ground realities. The project focuses on improving continuity of care, supporting health workers in following up with patients, and contributing to more organized and reliable maternal health records.

Earlier, Dr. Maryam received the Grand Challenges: Catalyzing Equitable Artificial Intelligence (AI) Use award from the Gates Foundation in support of this initiative. More recently, she was awarded the Google Award for Academic Research 2024, and The Patrick J. McGovern award which recognizes her contributions to inclusive and equitable AI development in healthcare settings.

The full article by the Gates Foundation can be accessed here.
 

In a world where security is paramount, the ability to protect personal information is constantly evolving. At SBASSE, a team of talented computer science researchers has uncovered a vulnerability in smartphone technology that could change the way we think about privacy.

The paper, "Glitch in Time: Exploiting Temporal Misalignment of IMU for Eavesdropping," has just been accepted to AsiaCCS 2025 (Core Rank A), a prestigious conference in the field of cybersecurity. With a competitive acceptance rate of only 15% in Cycle 1, this marks a significant achievement for the team, composed of Dr. Naveed Anwar Bhatti, Ahmed Najeeb, Abdul Rafay, and Dr. Muhammad Hamad Alizai.

What began as a simple class project for CS 677 in 2023 quickly turned into a journey of discovery. Ahmed and Abdul, both passionate about technology, set out to replicate existing research aimed at reconstructing audio from mobile accelerometer data. Their breakthrough came when they introduced a clever twist—misaligning the timing between the smartphone’s gyroscope and accelerometer. This allowed the gyroscope data to enhance the accelerometer data, making it possible to reconstruct voice commands at a lower sampling rate, all without requiring user permissions.
This discovery has profound implications for smartphone security. The ability to "listen" to your voice assistant commands without consent—using just two sensors at a sampling rate as low as 200 Hz—poses a major privacy risk. The vulnerability comes from the fact that these sensors don’t require user permission to operate at low rates, making them an ideal target for exploitation.

After months of hard work, the project blossomed into a senior-year SProj and was submitted to AsiaCCS 2025 in August 2024. The team's work has now earned them a place in one of the world’s top cybersecurity forums, where their research will undoubtedly inspire further innovations.

Dr. Naveed shares his pride, saying, “We can’t help but feel proud of Ahmed and Abdul, who poured their heart and soul into this project.”
Ahmed, now pursuing his PhD at Rochester Institute of Technology (RIT), and Abdul Rafay, who is continuing his academic journey as a Teaching Fellow in CS at LUMS, have “both proven that with dedication and creativity, the boundaries of what is possible in technology can be pushed even further.”

Congratulations to the team on their groundbreaking success!