Pith. sign in

REVIEW 1 major objections 48 references

Reviewed by Pith at T0; open to challenge.

T0 means a machine referee read the full paper against a public rubric. The mark states how deep the mechanical check went, never who wrote it. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.3

BayesWarp discovers more diverse neural network failures by mutating saliency-identified critical regions under uncertainty-aware Bayesian optimization while preserving proximity to the original data distribution.

2026-06-28 07:38 UTC pith:GAR23UPD

load-bearing objection BayesWarp combines saliency maps with Bayesian optimization to guide mutations toward neural net failures, but the abstract-only view leaves the size of the gains and the strength of the evidence unclear. the 1 major comments →

arxiv 2606.04314 v1 pith:GAR23UPD submitted 2026-06-03 cs.LG cs.SE

Testing Neural Networks via Bayesian-Guided Exploration of Decision Landscapes

Bin Duan , Meiru Che , Guowei Yang This is my paper
classification cs.LG cs.SE
keywords neural network testingBayesian optimizationsaliency mapsfailure discoverymodel robustnesstest case generationadversarial testing
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces BayesWarp, a testing framework that identifies decision-critical input regions with interpretable saliency techniques and guides adaptive mutations using uncertainty-aware Bayesian optimization. This setup targets the inefficiency of global mutation or coverage-guided methods in finding varied model failures without drifting from the training distribution or semantics. Evaluations on MNIST, CIFAR-10, and ImageNet across six models report gains in failure discovery rate, diversity of failures, test case quality, and critical neuron coverage within a fixed mutation budget. Fine-tuning the models on the generated failures further improves their performance. A sympathetic reader would care because reliable testing directly affects safety in deployed neural networks.

Core claim

BayesWarp addresses limitations in existing neural network testing by identifying decision-critical input regions via interpretable saliency techniques and adaptively guiding the testing process using an uncertainty-aware Bayesian Optimization strategy, enabling the discovery of diverse failures while preserving distributional and semantic proximity to the original data. Evaluation on MNIST, CIFAR-10, and ImageNet across six neural network models shows that BayesWarp improves failure discovery, failure diversity, test case quality, and critical neuron coverage under a fixed mutation budget. These results demonstrate that BayesWarp improves testing effectiveness. Moreover, fine-tuning with th

What carries the argument

The combination of saliency-based identification of decision-critical input regions with uncertainty-aware Bayesian Optimization to guide mutations adaptively.

Load-bearing premise

Mutating decision-critical regions identified by saliency maps and directed by Bayesian optimization will uncover more diverse failures while keeping test cases close to the original data distribution and semantics.

What would settle it

An experiment that applies the same mutation budget on the same six models and three datasets but replaces the saliency-plus-Bayesian guidance with uniform random region selection or standard global mutation, then measures whether failure count, diversity, and neuron coverage fail to show the reported gains.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • More model failures are uncovered under a fixed mutation budget compared to prior black-box or white-box methods.
  • The discovered failures exhibit greater diversity.
  • Test cases achieve higher quality and greater critical neuron coverage.
  • Fine-tuning models on the generated failure cases improves overall model performance.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The approach may complement rather than replace coverage-guided testing by supplying a focused exploration strategy within the same budget.
  • If saliency techniques can be defined for non-image inputs, the same Bayesian guidance could apply to testing in other modalities.
  • The uncertainty modeling inside the optimizer could support repeated testing rounds that progressively refine the failure set.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

1 major / 0 minor

Summary. The manuscript proposes BayesWarp, a testing framework for neural networks that mutates decision-critical input regions identified via interpretable saliency techniques, guided by an uncertainty-aware Bayesian Optimization strategy. The goal is to discover diverse model failures while preserving distributional and semantic proximity to the original data. Evaluation on MNIST, CIFAR-10, and ImageNet across six neural network models is claimed to show improvements in failure discovery, failure diversity, test case quality, and critical neuron coverage under a fixed mutation budget, with additional gains from fine-tuning on the generated failure cases.

Significance. If the empirical results hold under detailed scrutiny, the framework could provide a useful advance in efficient, distribution-preserving testing of neural networks for safety-critical applications by combining saliency-based localization with adaptive Bayesian search. The approach addresses a recognized tension between global mutation strategies and coverage-guided methods, but its significance cannot be fully assessed without access to the methods, quantitative results, and baseline comparisons.

major comments (1)
  1. Abstract: The central claims of improved failure discovery, diversity, test case quality, and critical neuron coverage (plus downstream fine-tuning gains) are stated without any quantitative metrics, baseline comparisons, statistical significance tests, or experimental protocol details. This prevents verification of whether the reported gains are load-bearing or merely incremental.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their detailed review and constructive feedback. We address the major comment below and outline the corresponding revision.

read point-by-point responses

  1. Referee: Abstract: The central claims of improved failure discovery, diversity, test case quality, and critical neuron coverage (plus downstream fine-tuning gains) are stated without any quantitative metrics, baseline comparisons, statistical significance tests, or experimental protocol details. This prevents verification of whether the reported gains are load-bearing or merely incremental.

    Authors: We agree that the abstract would be strengthened by the inclusion of key quantitative results. The current abstract is intentionally concise, with all supporting metrics, baseline comparisons, and experimental details provided in Sections 4 and 5 of the manuscript. In the revised version we will expand the abstract to report the primary numerical improvements (e.g., relative gains in failure discovery rate and diversity under the fixed budget) and note the evaluation protocol (MNIST, CIFAR-10, ImageNet; six models). We will also indicate where statistical significance was assessed. This change directly addresses the concern about verifiability while preserving the abstract's brevity. revision: yes

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper describes an empirical testing framework (BayesWarp) that applies saliency-based region identification and uncertainty-aware Bayesian optimization to generate test cases for neural networks. All load-bearing claims rest on reported experimental outcomes (failure discovery rates, diversity metrics, neuron coverage) measured against fixed mutation budgets on MNIST/CIFAR-10/ImageNet across six models. No equations, parameter-fitting steps, or self-citations are visible that would reduce any claimed result to a tautology or to the input data by construction. The framework components are standard external techniques whose effectiveness is assessed via independent benchmarks rather than internal redefinition.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract only; no specific free parameters, axioms, or invented entities are identifiable or detailed in the provided text.

pith-pipeline@v0.9.1-grok · 5691 in / 1059 out tokens · 34032 ms · 2026-06-28T07:38:21.528799+00:00 · methodology

0 comments
read the original abstract

As neural networks are increasingly deployed in safety-critical domains, testing is essential to evaluate and improve their reliability. Existing testing methods, whether black-box or white-box, primarily use global mutation or coverage-guided strategies, both of which struggle to efficiently uncover diverse model failures while remaining proximate to the original data distribution and semantics. We propose BayesWarp, a testing framework that addresses this limitation by mutating decision-critical input regions identified via interpretable saliency techniques and adaptively guiding the testing process using an uncertainty-aware Bayesian Optimization strategy, enabling the discovery of diverse failures while preserving distributional and semantic proximity to the original data. Evaluation on MNIST, CIFAR-10, and ImageNet across six neural network models shows that BayesWarp improves failure discovery, failure diversity, test case quality, and critical neuron coverage under a fixed mutation budget. These results demonstrate that BayesWarp improves testing effectiveness. Moreover, fine-tuning with the generated failure cases leads to improvements in model performance.

Figures

Figures reproduced from arXiv: 2606.04314 by Bin Duan, Guowei Yang, Meiru Che.

Figure 1
Figure 1. Figure 1: Overview of BAYESWARP A. Critical Region Localization We identify and localize decision-critical regions that are highly influential to model decisions. A saliency map H(x) ∈ R H×W is computed using a saliency-based interpretability method and normalized to [0, 1]. We retain the top-α propor￾tion of salient pixels by thresholding H(x) at the (1 − α) quantile: Tα = Quantile(H(x), 1 − α), M = 1(H(x) > Tα), w… view at source ↗
Figure 2
Figure 2. Figure 2: Comparison Results on DoF by the number of failure events across all seeds, with all methods executed on the same environment. Diversity of Failures (DoF), as used in previous works [7]– [9], [11], measures the number of distinct predicted classes different from the seed prediction observed among all failure￾inducing test cases. Frechet Inception Distance (FID) ´ , as used in prior work [8], quantifies dis… view at source ↗
Figure 3
Figure 3. Figure 3: Comparison Results on FID [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Comparison Results on SCS the quality of generated test cases, and the extent to which decision-critical internal behaviors are exercised. Accordingly, we assess BAYESWARP along four dimensions. First, failure discovery capability and efficiency are measured using the Number of Failures (NoF), Failure-inducing Seed Rate (FSR), and Time per Failure (TPF), which capture how frequently, consistently, and effi… view at source ↗
Figure 5
Figure 5. Figure 5: Test Accuracy Before and After Fine-Tuning for Different Testing Techniques. [PITH_FULL_IMAGE:figures/full_fig_p010_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Impact of Key Hyperparameters. Table IV shows that both components contribute to the ef￾fectiveness of BAYESWARP, but in different ways. Removing localization leads to consistent degradation across all metrics. NoF decreases by 1,265-3,069 and FSR drops by 0.18-0.54, indicating that a relatively large portion of the mutation budget becomes ineffective when mutations are no longer constrained to decision-cr… view at source ↗
Figure 7
Figure 7. Figure 7: Examples of Test Cases Generate by BAYESWARP 60 40 20 0 20 40 60 60 40 20 0 20 40 60 (a) LeNet-5 (MNIST) 60 40 20 0 20 40 60 80 60 40 20 0 20 40 60 80 (b) ResNet-18 (CIFAR-10) 75 50 25 0 25 50 75 100 75 50 25 0 25 50 75 100 (c) ResNet-50 (ImageNet) [PITH_FULL_IMAGE:figures/full_fig_p012_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: t-SNE visualization of penultimate-layer feature representations. [PITH_FULL_IMAGE:figures/full_fig_p012_8.png] view at source ↗

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

48 extracted references · 4 canonical work pages · 4 internal anchors

  1. [1]

    Convo- lutional neural networks,

    W. H. L. Pinaya, S. Vieira, R. Garcia-Dias, and A. Mechelli, “Convo- lutional neural networks,” inMachine learning. Elsevier, 2020, pp. 173–191

    2020

  2. [2]

    Stereo r-cnn based 3d object detection for autonomous driving,

    P. Li, X. Chen, and S. Shen, “Stereo r-cnn based 3d object detection for autonomous driving,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 7644–7652

    2019

  3. [3]

    Face recognition in unconstrained environment with cnn,

    H. Ben Fredj, S. Bouguezzi, and C. Souani, “Face recognition in unconstrained environment with cnn,”The Visual Computer, vol. 37, no. 2, pp. 217–226, 2021

    2021

  4. [4]

    Cnn-based android malware detection,

    M. Ganesh, P. Pednekar, P. Prabhuswamy, D. S. Nair, Y . Park, and H. Jeon, “Cnn-based android malware detection,” in2017 international conference on software security and assurance (ICSSA). IEEE, 2017, pp. 60–65

    2017

  5. [5]

    Deepxplore: Automated whitebox testing of deep learning systems,

    K. Pei, Y . Cao, J. Yang, and S. Jana, “Deepxplore: Automated whitebox testing of deep learning systems,” inproceedings of the 26th Symposium on Operating Systems Principles, 2017, pp. 1–18

    2017

  6. [6]

    Tensorfuzz: De- bugging neural networks with coverage-guided fuzzing,

    A. Odena, C. Olsson, D. Andersen, and I. Goodfellow, “Tensorfuzz: De- bugging neural networks with coverage-guided fuzzing,” inInternational Conference on Machine Learning. PMLR, 2019, pp. 4901–4911

    2019

  7. [7]

    Effective white-box testing of deep neural networks with adaptive neuron-selection strategy,

    S. Lee, S. Cha, D. Lee, and H. Oh, “Effective white-box testing of deep neural networks with adaptive neuron-selection strategy,” inProceedings of the 29th ACM SIGSOFT International Symposium on Software Testing and Analysis, 2020, pp. 165–176

    2020

  8. [8]

    Cit4dnn: Generating diverse and rare inputs for neural networks using latent space combinatorial testing,

    S. Dola, R. McDaniel, M. B. Dwyer, and M. L. Soffa, “Cit4dnn: Generating diverse and rare inputs for neural networks using latent space combinatorial testing,” inProceedings of the IEEE/ACM 46th International Conference on Software Engineering, 2024, pp. 1–13

    2024

  9. [9]

    Bet: black- box efficient testing for convolutional neural networks,

    J. Wang, H. Qiu, Y . Rong, H. Ye, Q. Li, Z. Li, and C. Zhang, “Bet: black- box efficient testing for convolutional neural networks,” inProceedings of the 31st ACM SIGSOFT International Symposium on Software Testing and Analysis, 2022, pp. 164–175

    2022

  10. [10]

    Neuron semantic-guided test generation for deep neural networks fuzzing,

    L. Huang, W. Sun, M. Yan, Z. Liu, Y . Lei, and D. Lo, “Neuron semantic-guided test generation for deep neural networks fuzzing,”ACM Transactions on Software Engineering and Methodology, vol. 34, no. 1, pp. 1–38, 2024

    2024

  11. [11]

    Diffchaser: Detecting disagreements for deep neural networks

    X. Xie, L. Ma, H. Wang, Y . Li, Y . Liu, and X. Li, “Diffchaser: Detecting disagreements for deep neural networks.” International Joint Conferences on Artificial Intelligence Organization, 2019

    2019

  12. [12]

    Atom: Automated black-box testing of multi-label image classification systems,

    S. Hu, H. Wu, P. Wang, J. Chang, Y . Tu, X. Jiang, X. Niu, and C. Nie, “Atom: Automated black-box testing of multi-label image classification systems,” in2023 38th IEEE/ACM International Conference on Auto- mated Software Engineering (ASE). IEEE, 2023, pp. 230–242

    2023

  13. [13]

    Dlfuzz: Differential fuzzing testing of deep learning systems,

    J. Guo, Y . Jiang, Y . Zhao, Q. Chen, and J. Sun, “Dlfuzz: Differential fuzzing testing of deep learning systems,” inProceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2018, pp. 739–743

    2018

  14. [14]

    Robot: Robustness-oriented testing for deep learning systems,

    J. Wang, J. Chen, Y . Sun, X. Ma, D. Wang, J. Sun, and P. Cheng, “Robot: Robustness-oriented testing for deep learning systems,” in2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE). IEEE, 2021, pp. 300–311

    2021

  15. [15]

    White-box test input generation for enhancing deep neural network models through suspicious neuron awareness,

    H. Guo, C. Tao, Z. Huang, and W. Zou, “White-box test input generation for enhancing deep neural network models through suspicious neuron awareness,”ACM Transactions on Software Engineering and Methodol- ogy, 2025

    2025

  16. [16]

    Is neuron coverage a meaningful measure for testing deep neural networks?

    F. Harel-Canada, L. Wang, M. A. Gulzar, Q. Gu, and M. Kim, “Is neuron coverage a meaningful measure for testing deep neural networks?” in Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2020, pp. 851–862

    2020

  17. [17]

    Revisiting neuron coverage metrics and quality of deep neural networks,

    Z. Yang, J. Shi, M. H. Asyrofi, and D. Lo, “Revisiting neuron coverage metrics and quality of deep neural networks,” in2022 IEEE Interna- tional Conference on Software Analysis, Evolution and Reengineering (SANER). IEEE, 2022, pp. 408–419

    2022

  18. [18]

    [Online]

    (2026) Bayeswarp. [Online]. Available: https://github.com/beanduan22/ BayesWarp /tree/main

    2026

  19. [19]

    On pixel-wise explanations for non-linear classifier deci- sions by layer-wise relevance propagation,

    S. Bach, A. Binder, G. Montavon, F. Klauschen, K.-R. M ¨uller, and W. Samek, “On pixel-wise explanations for non-linear classifier deci- sions by layer-wise relevance propagation,”PloS one, vol. 10, no. 7, p. e0130140, 2015

    2015

  20. [20]

    Grad-cam: Visual explanations from deep networks via gradient-based localization,

    R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-cam: Visual explanations from deep networks via gradient-based localization,” inProceedings of the IEEE international conference on computer vision, 2017, pp. 618–626. TRANSACTIONS ON SOFTW ARE ENGINEERING 15

    2017

  21. [21]

    Learning important features through propagating activation differences,

    A. Shrikumar, P. Greenside, and A. Kundaje, “Learning important features through propagating activation differences,” inInternational conference on machine learning. PMlR, 2017, pp. 3145–3153

    2017

  22. [22]

    Guided integrated gradients: An adaptive path method for removing noise,

    A. Kapishnikov, S. Venugopalan, B. Avci, B. Wedin, M. Terry, and T. Bolukbasi, “Guided integrated gradients: An adaptive path method for removing noise,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 5050–5058

    2021

  23. [23]

    SmoothGrad: removing noise by adding noise

    D. Smilkov, N. Thorat, B. Kim, F. Vi ´egas, and M. Wattenberg, “Smoothgrad: removing noise by adding noise,”arXiv preprint arXiv:1706.03825, 2017

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  24. [24]

    Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks,

    A. Chattopadhay, A. Sarkar, P. Howlader, and V . N. Balasubramanian, “Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks,” in2018 IEEE winter conference on applica- tions of computer vision (WACV). IEEE, 2018, pp. 839–847

    2018

  25. [25]

    A Tutorial on Bayesian Optimization

    P. I. Frazier, “A tutorial on bayesian optimization,”arXiv preprint arXiv:1807.02811, 2018

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  26. [26]

    Gaussian process regression for materials and molecules,

    V . L. Deringer, A. P. Bart ´ok, N. Bernstein, D. M. Wilkins, M. Ce- riotti, and G. Cs ´anyi, “Gaussian process regression for materials and molecules,”Chemical Reviews, vol. 121, no. 16, pp. 10 073–10 141, 2021

    2021

  27. [27]

    Expected improvement for expensive optimiza- tion: a review,

    D. Zhan and H. Xing, “Expected improvement for expensive optimiza- tion: a review,”Journal of Global Optimization, vol. 78, no. 3, pp. 507– 544, 2020

    2020

  28. [28]

    On bayesian upper confidence bounds for bandit problems,

    E. Kaufmann, O. Capp ´e, and A. Garivier, “On bayesian upper confidence bounds for bandit problems,” inArtificial intelligence and statistics. PMLR, 2012, pp. 592–600

    2012

  29. [29]

    A review of modern computational algorithms for bayesian optimal design,

    E. G. Ryan, C. C. Drovandi, J. M. McGree, and A. N. Pettitt, “A review of modern computational algorithms for bayesian optimal design,” International Statistical Review, vol. 84, no. 1, pp. 128–154, 2016

    2016

  30. [30]

    Variational learning of inducing variables in sparse gaussian processes,

    M. Titsias, “Variational learning of inducing variables in sparse gaussian processes,” inArtificial intelligence and statistics. PMLR, 2009, pp. 567–574

    2009

  31. [31]

    Mnist handwritten digit database,

    Y . LeCun, C. Cortes, and C. J. Burges, “Mnist handwritten digit database,” http://yann.lecun.com/exdb/mnist, 2010

    2010

  32. [32]

    Gradient-based learning applied to document recognition,

    Y . LeCun, L. Bottou, Y . Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,”Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998

    1998

  33. [33]

    Learning multiple layers of features from tiny images,

    A. Krizhevsky and G. Hinton, “Learning multiple layers of features from tiny images,” https://www.cs.toronto.edu/ ∼kriz/ learning-features-2009-TR.pdf, Citeseer, Tech. Rep., 2009

    2009

  34. [34]

    Very Deep Convolutional Networks for Large-Scale Image Recognition

    K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,”arXiv preprint arXiv:1409.1556, 2014

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  35. [35]

    Deep residual learning for image recognition,

    K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” inProceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778

    2016

  36. [36]

    Imagenet: A large-scale hierarchical image database,

    J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “Imagenet: A large-scale hierarchical image database,” in2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2009, pp. 248–255

    2009

  37. [37]

    Learning transferable visual models from natural language supervi- sion,

    A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark, G. Krueger, and I. Sutskever, “Learning transferable visual models from natural language supervi- sion,” inProceedings of the 38th International Conference on Machine Learning, 2021

    2021

  38. [38]

    Deepgauge: Multi-granularity testing criteria for deep learning systems,

    L. Ma, F. Juefei-Xu, F. Zhang, J. Sun, M. Xue, B. Li, C. Chen, T. Su, L. Li, Y . Liuet al., “Deepgauge: Multi-granularity testing criteria for deep learning systems,” inProceedings of the 33rd ACM/IEEE international conference on automated software engineering, 2018, pp. 120–131

    2018

  39. [39]

    Criticalfuzz: A critical neuron coverage-guided fuzz testing framework for deep neural networks,

    T. Bai, S. Huang, Y . Huang, X. Wang, C. Xia, Y . Qu, and Z. Yang, “Criticalfuzz: A critical neuron coverage-guided fuzz testing framework for deep neural networks,”Information and Software Technology, vol. 172, p. 107476, 2024

    2024

  40. [40]

    A survey on adversarial attacks and defences,

    A. Chakraborty, M. Alam, V . Dey, A. Chattopadhyay, and D. Mukhopad- hyay, “A survey on adversarial attacks and defences,”CAAI Transactions on Intelligence Technology, vol. 6, no. 1, pp. 25–45, 2021

    2021

  41. [41]

    Adversarial Attacks on Neural Network Policies

    S. Huang, N. Papernot, I. Goodfellow, Y . Duan, and P. Abbeel, “Adversarial attacks on neural network policies,”arXiv preprint arXiv:1702.02284, 2017

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  42. [42]

    Evaluating the robustness of deep learning models against adversarial attacks: An analysis with fgsm, pgd and cw,

    W. Villegas-Ch, A. Jaramillo-Alc ´azar, and S. Luj ´an-Mora, “Evaluating the robustness of deep learning models against adversarial attacks: An analysis with fgsm, pgd and cw,”Big Data and Cognitive Computing, vol. 8, no. 1, p. 8, 2024

    2024

  43. [43]

    Deephunter: a coverage-guided fuzz testing framework for deep neural networks,

    X. Xie, L. Ma, F. Juefei-Xu, M. Xue, H. Chen, Y . Liu, J. Zhao, B. Li, J. Yin, and S. See, “Deephunter: a coverage-guided fuzz testing framework for deep neural networks,” inProceedings of the 28th ACM SIGSOFT international symposium on software testing and analysis, 2019, pp. 146–157

    2019

  44. [44]

    Deeptest: Automated testing of deep-neural-network-driven autonomous cars,

    K. Pei, Y . Cao, J. Yang, and S. Jana, “Deeptest: Automated testing of deep-neural-network-driven autonomous cars,” inProceedings of the 40th International Conference on Software Engineering, 2018, pp. 303– 314

    2018

  45. [45]

    Sinvad: Search-based image space nav- igation for dnn image classifier test input generation,

    S. Kang, R. Feldt, and S. Yoo, “Sinvad: Search-based image space nav- igation for dnn image classifier test input generation,” inProceedings of the IEEE/ACM 42nd International Conference on Software Engineering Workshops, 2020, pp. 521–528

    2020

  46. [46]

    Improving deep learning interpretability by saliency guided training,

    A. A. Ismail, H. Corrada Bravo, and S. Feizi, “Improving deep learning interpretability by saliency guided training,”Advances in Neural Infor- mation Processing Systems, vol. 34, pp. 26 726–26 739, 2021

    2021

  47. [47]

    Scgan: Saliency map-guided colorization with generative adversarial network,

    Y . Zhao, L.-M. Po, K.-W. Cheung, W.-Y . Yu, and Y . A. U. Rehman, “Scgan: Saliency map-guided colorization with generative adversarial network,”IEEE Transactions on Circuits and Systems for Video Tech- nology, vol. 31, no. 8, pp. 3062–3077, 2020

    2020

  48. [48]

    Adversarial example detection based on saliency map features,

    S. Wang and Y . Gong, “Adversarial example detection based on saliency map features,”Applied Intelligence, vol. 52, no. 6, pp. 6262–6275, 2022

    2022