Publications

Embedding-based Diversity Mapping for Test Generator Selection and Input Prioritization in Grammar-based Testing

Shifat Sahariar Bhuiyan, Nargiz Humbatova, Paolo Tonella

ICST'26

Revisiting" Revisiting Neuron Coverage for DNN Testing: A Layer-Wise and Distribution-Aware Criterion": A Critical Review and Implications on DNN Coverage Testing

Jinhan Kim, Nargiz Humbatova, Gunel Jahangirova, Shin Yoo, Paolo Tonella

ICSE'26

TopoMap: A Feature-based Semantic Discriminator of the Topographical Regions in the Test Input Space

Gianmarco De Vita, Nargiz Humbatova, Paolo Tonella

arXiv'25

New Formulation of DNN Statistical Mutation Killing for Ensuring Monotonicity: A Technical Report

Jinhan Kim, Nargiz Humbatova, Gunel Jahangirova, Shin Yoo, Paolo Tonella

arXiv'25

Fault Localisation and Repair for DL Systems: An Empirical Study with LLMs

Jinhan Kim, Nargiz Humbatova, Gunel Jahangirova, Shin Yoo, Paolo Tonella

arXiv'25

An Empirical Study of Fault Localisation Techniques for Deep Neural Networks

Nargiz Humbatova, Jinhan Kim, Gunel Jahangirova, Shin Yoo, Paolo Tonella

EMSE'25

MuFF: Stable and Sensitive Post-training Mutation Testing for Deep Learning

Jinhan Kim, Nargiz Humbatova, Gunel Jahangirova, Shin Yoo, Paolo Tonella

arXiv'25

Real Faults in Deep Learning Fault Benchmarks: How Real Are They?

Gunel Jahangirova, Nargiz Humbatova, Jinhan Kim, Shin Yoo, Paolo Tonella

arXiv'25

µPRL: a Mutation Testing Pipeline for Deep Reinforcement Learning based on Real Faults

Deepak-George Thomas, Matteo Biagiola, Nargiz Humbatova, Mohammad Wardat, Gunel Jahangirova, Hridesh Rajan, Paolo Tonella

ICSE'25

µPRL: a Mutation Testing Pipeline for Deep Reinforcement Learning based on Real Faults

Deepak-George Thomas, Matteo Biagiola, Nargiz Humbatova, Mohammad Wardat, Gunel Jahangirova, Hridesh Rajan, Paolo Tonella

ICSE'25

Spectral Analysis of the Relation between Deep Learning Faults and Neural Activation Values

Nargiz Humbatova, Gunel Jahangirova, Paolo Tonella

ICST'24

DeepCrime: from Real Faults to Mutation Testing Tool for Deep Learning

Nargiz Humbatova, Gunel Jahangirova, Paolo Tonella

ICSE Companion'23

Repairing DNN Architecture: Are We There Yet?

Jinhan Kim, Nargiz Humbatova, Gunel Jahangirova, Paolo Tonella, Shin Yoo

ICST'23

DeepMetis: Augmenting a Deep Learning Test Set to Increase its Mutation Score

Vincenzo Riccio, Humbatova Nargiz, Gunel Jahangirova, and Paolo Tonella

ASE'21

DeepCrime: Mutation Testing of Deep Learning Systems based on Real Faults

Humbatova Nargiz, Gunel Jahangirova, and Paolo Tonella

ISSTA'21

Taxonomy of real faults in deep learning systems

Humbatova Nargiz, Gunel Jahangirova, Gabriele Bavota, Vincenzo Riccio, Andrea Stocco, 

and Paolo Tonella

ICSE'20

Testing machine learning based systems: a systematic mapping

Vincenzo Riccio, Jahangirova Gunel, Andrea Stocco, Nargiz Humbatova, Michael Weiss, 

and Paolo Tonella

Empirical Software Engineering (2020)