activity
20242026
collaborators

5 papers

cs.CV2026

Effort-Optimized, Accuracy-Driven Labelling and Validation of Test Inputs for DL Systems: A Mixed-Integer Linear Programming Approach

Mohammad Hossein Amini, Mehrdad Sabetzadeh, Shiva Nejati

Software systems increasingly include AI components based on deep learning (DL). Reliable testing of such systems requires near-perfect test-input validity and label accuracy, with…

cs.SE2025

Test Input Validation for Vision-based DL Systems: An Active Learning Approach

Delaram Ghobari, Mohammad Hossein Amini, Dai Quoc Tran +3

Testing deep learning (DL) systems requires extensive and diverse, yet valid, test inputs. While synthetic test input generation methods, such as metamorphic testing, are widely us…

cs.SE2024

Can Search-Based Testing with Pareto Optimization Effectively Cover Failure-Revealing Test Inputs?

Lev Sorokin, Damir Safin, Shiva Nejati

Search-based software testing (SBST) is a widely adopted technique for testing complex systems with large input spaces, such as Deep Learning-enabled (DL-enabled) systems. Many SBS…

cs.SE2024

Bridging the Gap between Real-world and Synthetic Images for Testing Autonomous Driving Systems

Mohammad Hossein Amini, Shiva Nejati

Deep Neural Networks (DNNs) for Autonomous Driving Systems (ADS) are typically trained on real-world images and tested using synthetic simulator images. This approach results in tr…

cs.SE2024

Generating Minimalist Adversarial Perturbations to Test Object-Detection Models: An Adaptive Multi-Metric Evolutionary Search Approach

Cristopher McIntyre-Garcia, Adrien Heymans, Beril Borali +2

Deep Learning (DL) models excel in computer vision tasks but can be susceptible to adversarial examples. This paper introduces Triple-Metric EvoAttack (TM-EVO), an efficient algori…