Metraipolis › archive › dc_a484f0ff141f

FuzzInsight: Navigating the Efficiency-Effectiveness Trade-off in Coverage-Guided DNN Fuzzing — arXiv:2610.23195

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.23195
License (as archived)
CC0-1.0
Archived
2026-10-19T08:42:30.308Z
SHA-256 of the archived text
56f22326480cc0fadbd821be8459d8d64c38a574556ea2b08825f35aac1ceecc
Stable URL of this page
https://metraipolis.com/documento/dc_a484f0ff141f

How to cite

FuzzInsight: Navigating the Efficiency-Effectiveness Trade-off in Coverage-Guided DNN Fuzzing — arXiv:2610.23195 — arXiv (en), https://arxiv.org/abs/2610.23195 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a484f0ff141f (Metraipolis archive dc_a484f0ff141f, sha256 56f22326480cc0fadbd821be8459d8d64c38a574556ea2b08825f35aac1ceecc)
BibTeX
@misc{dca484f0ff141f,
  title = {FuzzInsight: Navigating the Efficiency-Effectiveness Trade-off in Coverage-Guided DNN Fuzzing — arXiv:2610.23195},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23195},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a484f0ff141f; sha256 56f22326480cc0fadbd821be8459d8d64c38a574556ea2b08825f35aac1ceecc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23195. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Collecting and labeling diverse test datasets for evaluating Deep Neural Networks (DNNs) is costly and time-consuming. This has motivated coverage-guided fuzzing techniques that generate defect-revealing corner cases from limited test data. However, their effectiveness depends heavily on configuration choices, particularly coverage criteria and seed-selection strategies. We present a configuration-oriented analysis and decision guidelines for scalable DNN fuzzing targeting two bottlenecks: inefficient seed utilization and the cost of coverage guidance. Our analysis shows that existing seed-selection strategies repeatedly prioritize a small subset of inputs, leaving many collected seeds unexplored. To address this issue, we propose Equalized Sampling, a constraint-based strategy that increases mean seed queue utilization to 77%, improving on prior approaches by 13 percentage points. We further evaluate 84 fuzzing configurations on four benchmark datasets: MNIST, SVHN, GTSRB, and CIFAR-100. Results show that the non-structural criteria LSCD, LSC, and MDSC achieve coverage outcomes comparable to structural and alternative non-structural criteria while requiring substantially less computation. These criteria also promote broad behavioral exploration of the DNN under test, reducing the need to monitor multiple coverage metrics. Among them, LSCD provides a modest but consistent runtime advantage. Finally, we show that retraining with generated corner cases improves generalization robustness by up to 77 percentage points on average without degrading performance on the original test distribution. Together, these findings provide a practical blueprint for selecting fuzzing configurations that balance efficiency, behavioral exploration, and model hardening.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.23195 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T08:39:10.066Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).