mlsanityData to 7 Oct 2026

Latent Regularization in Generative Test Input Generation

arXiv 2602.15552 ↗First posted 17 Feb 2026cs.SE cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

This study investigates the impact of regularization of latent spaces through truncation on the quality of generated test inputs for deep learning classifiers. We evaluate this effect using style-based GANs, a state-of-the-art generative approach, and assess quality along three dimensions: validity, diversity, and fault detection. We evaluate our approach on the boundary testing of deep learning image classifiers across three datasets, MNIST, Fashion MNIST, and CIFAR-10. We compare two truncation strategies: latent code mixing with binary search optimization and random latent truncation for generative exploration. Our experiments show that the latent code-mixing approach yields a higher fault detection rate than random truncation, while also improving both diversity and validity.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 50 references that are in the map. First posted on arXiv 17 Feb 2026.

Builds on

28 of 50 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  5. 2016Improved Techniques for Training GANscited by 2,938
  6. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  7. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  8. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  9. 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
  10. 2018Assessing Generative Models via Precision and Recallcited by 401
  11. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  12. 2017DeepXplore: Automated Whitebox Testing of Deep Learning Systemscited by 307
16 more
  1. 2017DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Carscited by 249
  2. 2018DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systemscited by 144
  3. 2019Taxonomy of Real Faults in Deep Learning Systemscited by 90
  4. 2018TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzingcited by 67
  5. 2018DLFuzz: Differential Fuzzing Testing of Deep Learning Systemscited by 64
  6. 2020Model-based Exploration of the Frontier of Behaviours for Deep Learning System Testingcited by 40
  7. 2021DeepHyperion: Exploring the Feature Space of Deep Learning-Based Systems through Illumination Searchcited by 29
  8. 2020SINVAD: Search-based Image Space Navigation for DNN Image Classifier Test Input Generationcited by 15
  9. 2024Assessing Quality Metrics for Neural Reality Gap Input Mitigation in Autonomous Driving Testingcited by 15
  10. 2024Predicting Safety Misbehaviours in Autonomous Driving Systems using Uncertainty Quantificationcited by 11
  11. 2022Generating and Detecting True Ambiguity: A Forgotten Danger in DNN Supervision Testingcited by 8
  12. 2024Benchmarking Generative AI Models for Deep Learning Test Input Generationcited by 4
  13. 2025Benchmarking Image Perturbations for Testing Automated Driving Assistance Systemscited by 4
  14. 2024Targeted Deep Learning System Boundary Testingcited by 3
  15. 2025XMutant: XAI-based Fuzzing for Deep Learning Systemscited by 3
  16. 2025A Multi-Modality Evaluation of the Reality Gap in Autonomous Driving Systemscited by 1

Built on by

Not cited yet.