Latent Anchor-Driven Test Generation for Deep Neural Networks

• URL: http://arxiv.org/abs/2606.04310v1
• Date: Wed, 03 Jun 2026 00:33:21 GMT
• Title: Latent Anchor-Driven Test Generation for Deep Neural Networks
• Abstract summary: Latte is a black-box testing framework for Deep Neural Networks (DNNs)<n>It generates semantically proximate, diverse, and fault-revealing test cases by leveraging the latent space.<n>We evaluate Latte on 5 datasets and 10 DNN models in single-model and multi-model testing scenarios.
• Score: 21.287972204772515
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep Neural Networks (DNNs) are increasingly being deployed in security-critical and safety-sensitive applications, which makes rigorous testing essential to identify and mitigate model weaknesses. Existing DNN testing approaches explore either the input space or a learned latent space. While latent-space generation can better maintain plausibility than direct input-space mutation, current methods still face a trade-off among exploration controllability, failure diversity, and seed-relative semantic drift. To overcome these limitations, we propose Latte, a black-box testing framework that generates semantically proximate, diverse, and fault-revealing test cases by leveraging the latent space. Specifically, Latte encodes each input seed with a pre-trained VQ-VAE and performs a seed-centered, one-step latent mutation along directions defined by anchors sampled from alternative classes, followed by quantization and decoding back to the input space. This explores local neighborhoods around each seed within the learned latent manifold, resulting in a larger number and broader diversity of oracle-triggering prediction discrepancies under the same budget. We evaluated Latte on 5 datasets and 10 DNN models in single-model and multi-model testing scenarios. Across the evaluated datasets and models, Latte improves fault exposure and behavioral diversity under matched testing budgets. Under the single-model setting, it also maintains low seed-relative semantic drift with respect to the source seeds.

Related papers

• Reliable Neural Collapse Approximation for Open-World Test-Time Adaptation [95.55552104238787]
  Test-Time Adaptation (TTA) methods aim to bridge the domain gap between the source and target domains.<n>Traditional TTA methods become ineffective when the label distribution shift occurs.<n>We introduce a new method named Reliable Neural Collapse approximation (ReNC) for Open-World Test-Time Adaptation.
  arXiv  Detail & Related papers  (2026-08-20T10:57:44Z)
• Generating Realistic, Diverse, and Fault-Revealing Inputs with Latent Space Interpolation for Testing Deep Neural Networks [23.018072013940245]
  ARGUS is a black-box method to generate realistic, diverse, and fault-revealing test inputs.<n>ARGUS excels in generating realistic and diverse adversarial samples relative to the target dataset.<n>Using adversarial samples for model retraining can improve model classification accuracy.
  arXiv  Detail & Related papers  (2025-03-22T03:19:55Z)
• Generative Edge Detection with Stable Diffusion [52.870631376660924]
  Edge detection is typically viewed as a pixel-level classification problem mainly addressed by discriminative methods. We propose a novel approach, named Generative Edge Detector (GED), by fully utilizing the potential of the pre-trained stable diffusion model. We conduct extensive experiments on multiple datasets and achieve competitive performance.
  arXiv  Detail & Related papers  (2024-10-04T01:52:23Z)
• DOTA: Distributional Test-Time Adaptation of Vision-Language Models [69.41389326333771]
  Vision-language foundation models can be unreliable when significant distribution gaps exist between training and test data.<n>We propose DOTA (DistributiOnal Test-time Adaptation), a simple yet effective method addressing this limitation.<n>This distribution-centric approach enables the model to continually learn and adapt to the deployment environment.
  arXiv  Detail & Related papers  (2024-09-28T15:03:28Z)
• Tilt your Head: Activating the Hidden Spatial-Invariance of Classifiers [0.7704032792820767]
  Deep neural networks are applied in more and more areas of everyday life. They still lack essential abilities, such as robustly dealing with spatially transformed input signals. We propose a novel technique to emulate such an inference process for neural nets.
  arXiv  Detail & Related papers  (2024-05-06T09:47:29Z)
• MUAD: Multiple Uncertainties for Autonomous Driving benchmark for multiple uncertainty types and tasks [10.624564056837835]
  MUAD dataset consists of 8,500 realistic synthetic images with diverse adverse weather conditions. This dataset allows to better assess the impact of different sources of uncertainty on model performance.
  arXiv  Detail & Related papers  (2022-03-02T22:14:12Z)
• GAN Based Boundary Aware Classifier for Detecting Out-of-distribution Samples [24.572516991009323]
  We propose a GAN based boundary aware classifier (GBAC) for generating a closed hyperspace which only contains most id data. Our method is based on the fact that the traditional neural net seperates the feature space as several unclosed regions which are not suitable for ood detection. With GBAC as an auxiliary module, the ood data distributed outside the closed hyperspace will be assigned with much lower score, allowing more effective ood detection.
  arXiv  Detail & Related papers  (2021-12-22T03:35:54Z)
• DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows [52.31831255787147]
  We introduce a novel technique, DAAIN, to detect out-of-distribution (OOD) inputs and adversarial attacks (AA) Our approach monitors the inner workings of a neural network and learns a density estimator of the activation distribution. Our model can be trained on a single GPU making it compute efficient and deployable without requiring specialized accelerators.
  arXiv  Detail & Related papers  (2021-05-30T22:07:13Z)
• Attribute-Guided Adversarial Training for Robustness to Natural Perturbations [64.35805267250682]
  We propose an adversarial training approach which learns to generate new samples so as to maximize exposure of the classifier to the attributes-space. Our approach enables deep neural networks to be robust against a wide range of naturally occurring perturbations.
  arXiv  Detail & Related papers  (2020-12-03T10:17:30Z)
• Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders [63.46738617561255]
  We consider the problem of sparsifying the discrete latent space of a trained conditional variational autoencoder. We use evidential theory to identify the latent classes that receive direct evidence from a particular input condition and filter out those that do not. Experiments on diverse tasks, such as image generation and human behavior prediction, demonstrate the effectiveness of our proposed technique.
  arXiv  Detail & Related papers  (2020-10-19T01:27:21Z)
• SINVAD: Search-based Image Space Navigation for DNN Image Classifier Test Input Generation [0.0]
  Testing of Deep Neural Networks (DNNs) has become increasingly important as DNNs are widely adopted by safety critical systems. Current testing techniques for DNNs depend on small local perturbations to existing inputs. We propose new ways to search not over the entire image space, but rather over a plausible input space that resembles the true training distribution.
  arXiv  Detail & Related papers  (2020-05-19T09:06:21Z)
• Diversity inducing Information Bottleneck in Model Ensembles [73.80615604822435]
  In this paper, we target the problem of generating effective ensembles of neural networks by encouraging diversity in prediction. We explicitly optimize a diversity inducing adversarial loss for learning latent variables and thereby obtain diversity in the output predictions necessary for modeling multi-modal data. Compared to the most competitive baselines, we show significant improvements in classification accuracy, under a shift in the data distribution.
  arXiv  Detail & Related papers  (2020-03-10T03:10:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.