SASharmin Afrose

Sharmin Afrose

*This is an algorithmically generated author record based on publicly available information.

Sharmin Afrose has a total of 37 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Algorithmic Bias in Suicide Risk Prediction Models

    by Sharmin Afrose, Snehalatha Reddy Eggina, Jorge Ramirez Osorio, Anuj Kapadia, Jodie Trafton, Alina Peluso

  • Open Access

    Being the Developers’ Friend: Our Experience Developing a High-Precision Tool for Secure Coding

    by Danfeng Daphne Yao, Sazzadur Rahaman, Ya Xiao, Sharmin Afrose, Miles Frantz, Ke Tian, Na Meng, Cristina Cifuentes, Yang Zhao, Nicholas Allen, et al.


  • Evaluation of Static Vulnerability Detection Tools With Java Cryptographic API Benchmarks

    by Sharmin Afrose, Ya Xiao, Sazzadur Rahaman, Barton P. Miller, Danfeng Daphne Yao

    Several studies showed that misuses of cryptographic APIs are common in real-world code (e.g., Apache projects and Android apps). There exist several open-sourced and commercial security tools that automatically screen Java programs to detect misuses. To compare their accuracy and security guarantees, we develop two comprehensive benchmarks named CryptoAPI-Bench and Apache-Bench. CryptoAPI-Bench consists of 181 unit test cases that cover basic cases, as well as complex cases, including interprocedural, field sensitive, multiple class test cases, and path sensitive data flow of misuse cases. The benchmark also includes correct cases for testing false-positive rates. The Apache-Bench consists of 122 cryptographic cases from 10 Apache projects. We evaluate four tools, namely, SpotBugs, CryptoGuard, CrySL, and Coverity using both benchmarks. We present their performance and comparative analysis. The Apache-Bench also examines the scalability of the tools. Our benchmarks are useful for advancing state-of-the-art solutions in the space of misuse detection.


  • Open Access

    Measurement of Local Differential Privacy Techniques for IoT-based Streaming Data

    by Sharmin Afrose, Danfeng Daphne Yao, Olivera Kotevska

    Various Internet of Things (IoT) devices generate complex, dynamically changed, and infinite data streams. Adversaries can cause harm if they can access the user’s sensitive raw streaming data. For this reason, protecting the privacy of the data streams is crucial. In this paper, we explore local differential privacy techniques for streaming data. We compare the techniques and report the advantages and limitations. We also present the effect on component (e.g., smoother, perturber) variations of distribution-based local differential privacy. We find that combining distribution-based noise during perturbation provides more flexibility to the interested entity.


  • Open Access

    Subpopulation-specific Machine Learning Prognosis for Underrepresented Patients with Double Prioritized Bias Correction

    by Sharmin Afrose, Wenjia Song, Charles B. Nemeroff, Chang Lu, Danfeng (Daphne) Yao

    Background: Many clinical datasets are intrinsically imbalanced, dominated by overwhelming majority groups. Off-the-shelf machine learning models that optimize the prognosis of majority patient types (e.g., healthy class) may cause substantial errors on the minority prediction class (e.g., disease class) and demographic subgroups (e.g., Black or young patients). In the typical one-machine-learning-model-fits-all paradigm, racial and age disparities are likely to exist, but unreported. In addition, some widely used whole-population metrics give misleading results. Methods: We design a double prioritized (DP) bias correction technique to mitigate representational biases in machine learning-based prognosis. Our method trains customized machine learning models for specific ethnicity or age groups, a substantial departure from the one-model-predicts-all convention. We compare with other sampling and reweighting techniques in mortality and cancer survivability prediction tasks. Results: We first provide empirical evidence showing various prediction deficiencies in a typical machine learning setting without bias correction. For example, missed death cases are 3.14 times higher than missed survival cases for mortality prediction. Then, we show DP consistently boosts the minority class recall for underrepresented groups, by up to 38.0%. DP also reduces relative disparities across race and age groups, e.g., up to 88.0% better than the 8 existing sampling solutions in terms of the relative disparity of minority class recall. Cross-race and cross-age-group evaluation also suggests the need for subpopulation-specific machine learning models. Conclusions: Biases exist in the widely accepted one-machine-learning-model-fits-all-population approach. We invent a bias correction method that produces specialized machine learning prognostication models for underrepresented racial and age groups. This technique may reduce life-threatening prediction mistakes for minority populations. Plain Language Summary: This work aims to improve the prediction accuracy of machine learning models in medical applications, e.g., estimating the likelihood of a patient dying in an emergency room visit or surviving cancer. Inaccurate prediction may produce life-threatening consequences. We first examine how biases in training data impact prediction outcomes, in particular how underrepresented patients (e.g., young patients or patients of color) are impacted. Then, we design a double prioritized (DP) bias correction technique. It allows one to train machine learning models for specific demographic groups, e.g., one machine learning model for Black patients and another model for Asian patients. Our results confirm the need for training subpopulation-specific machine learning models. Our work helps improve the medical care of minority patients in the age of digital health.


  • Open Access

    A Comprehensive Benchmark on Java Cryptographic API Misuses

    by Sharmin Afrose, Sazzadur Rahaman, Danfeng (Daphne) Yao

    Misuses of cryptographic APIs are prevalent in existing real-world Java code. Some open-sourced and commercial cryptographic vulnerability detection tools exist that capture misuses in Java program. To analyze their efficiency and coverage, we build a comprehensive benchmark named CryptoAPI-Bench that consists of 171 unit test cases. The test cases include basic cases and complex cases. We assess four tools i.e., SpotBugs, CryptoGuard, CrySL, and Coverity using CryptoAPI-Bench and show their relative performance.


  • Open Access

    CryptoGuard: High Precision Detection of Cryptographic Vulnerabilities in Massive-sized Java Projects

    by Sazzadur Rahaman, Ya Xiao, Sharmin Afrose, Fahad Shaon, Ke Tian, Miles Frantz, Danfeng, Daphne Yao, Murat Kantarcioglu

    Cryptographic API misuses, such as exposed secrets, predictable random numbers, and vulnerable certificate verification, seriously threaten software security. The vision of automatically screening cryptographic API calls in massive-sized (e.g., millions of LoC) Java programs is not new. However, hindered by the practical difficulty of reducing false positives without compromising analysis quality, this goal has not been accomplished. State-of-the-art crypto API screening solutions are not designed to operate on a large scale. Our technical innovation is a set of fast and highly accurate slicing algorithms. Our algorithms refine program slices by identifying language-specific irrelevant elements. The refinements reduce false alerts by 76% to 80% in our experiments. Running our tool, CrytoGuard, on 46 high-impact large-scale Apache projects and 6,181 Android apps generate many security insights. Our findings helped multiple popular Apache projects to harden their code, including Spark, Ranger, and Ofbiz. We also have made substantial progress towards the science of analysis in this space, including: i) manually analyzing 1,295 Apache alerts and confirming 1,277 true positives (98.61% precision), ii) creating a benchmark with 38-unit basic cases and 74-unit advanced cases, iii) performing an in-depth comparison with leading solutions including CrySL, SpotBugs, and Coverity. We are in the process of integrating CryptoGuard with the Software Assurance Marketplace (SWAMP).

  • Open Access

    Towards Privacy-preserving Authenticated Disease Risk Queries

    by Nusrat Jahan Mozumder, Maitraye Das, Tanzima Hashem, Sharmin Afrose, Khandakar Ashrafi Akbar

    Recent improvement in genomic research is paving the way towards significant progress in diagnosis and treatment of diseases. A disease risk query returns the probability of a patient to develop a particular disease based on her genomic and clinical data. Despite various innovative prospects, frequent and ubiquitous usage of genomic data in medical tests and personalized medicine may cause various privacy threats like genetic discrimination, exposure of susceptibility to diseases, and revelation of genomic data of relatives. Another major concern is on ensuring the reliability of the genome data and the correctness of the computed disease risk, which is known as authentication. We develop a novel secret sharing approach to protect privacy of sensitive genomic and clinical data, disease markers, disease name, and the query answer while ensuring authenticated result of the disease risk query. In addition, we discuss the applicability of our approach in the field of personalized medicine. We perform a comprehensive security analysis for our system. Experiments with real datasets show that our approach for authenticated disease risk queries achieves a high level of privacy with reduced processing and storage overhead.


  • Numerical study on ITO surface modification technique to improve single emissive layer based organic light emitting diode performance

    by Riku Chowdhury, Rashedul Haq, Sarwar Uddin Chowdhury, Sharmin Afrose, Sukanta Paul

    To improve the performance and operational life time of an organic light emitting diode (OLED), a single uniformly mixed-host (MH) emissive layer (EML) based OLED structure with modified anode surface has been proposed in this work. Through the numerical simulation, the feasibility of the proposed modified work function of ITO based device structure has been justified from the electrical characteristics and efficiency curves. By the ITO surface modification technique, the interfacial energy barrier of ITO/EML is reduced enough to increase hole injection rate into the EML. Therefore, the carriers become more balanced which raise the recombination rate in the EML. From the calculated current balance factor from the simulation results, it is confirmed that due to ITO surface modification, the proposed MH-OLED able to give better performance in terms of brightness, efficiency and longer operating time over unmodified ITO based MH-OLED.