mlsanityData to 14 Oct 2026

CGDTest: A Constrained Gradient Descent Algorithm for Testing Neural Networks

arXiv 2304.01826 ↗First posted 4 Apr 2023cs.LG cs.SEcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a new Deep Neural Network (DNN) testing algorithm called the Constrained Gradient Descent (CGD) method, and an implementation we call CGDTest aimed at exposing security and robustness issues such as adversarial robustness and bias in DNNs. Our CGD algorithm is a gradient-descent (GD) method, with the twist that the user can also specify logical properties that characterize the kinds of inputs that the user may want. This functionality sets CGDTest apart from other similar DNN testing tools since it allows users to specify logical constraints to test DNNs not only for ℓp ball-based adversarial robustness but, more importantly, includes richer properties such as disguised and flow adversarial constraints, as well as adversarial robustness in the NLP domain. We showcase the utility and power of CGDTest via extensive experimentation in the context of vision and NLP domains, comparing against 32 state-of-the-art methods over these diverse domains. Our results indicate that CGDTest outperforms state-of-the-art testing tools for ℓp ball-based adversarial robustness, and is significantly superior in testing for other adversarial robustness, with improvements in PAR2 scores of over 1500% in some cases over the next best tool. Our evaluation shows that our CGD method outperforms competing methods we compared against in terms of expressibility (i.e., a rich constraint language and concomitant tool support to express a wide variety of properties), scalability (i.e., can be applied to very large real-world models with up to 138 million parameters), and generality (i.e., can be used to test a plethora of model architectures).

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 59 references that are in the map. First posted on arXiv 4 Apr 2023.

Builds on

25 of 59 references.

References · 25

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  4. 2016Adversarial examples in the physical worldcited by 1,769
  5. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  6. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  7. 2019Algorithms for Verifying Deep Neural Networkscited by 221
  8. 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 205
  9. 2018Spatially Transformed Adversarial Examplescited by 195
  10. 2020NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systemscited by 128
  11. 2022General Cutting Planes for Bound-Propagation-Based Neural Network Verificationcited by 103
  12. 2022Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Boundcited by 92
13 more
  1. 2019Training individually fair ML models with Sensitive Subspace Robustnesscited by 73
  2. 2021The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Resultscited by 71
  3. 2020TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLPcited by 45
  4. 2021Improved Branch and Bound for Neural Network Verification via Lagrangian Decompositioncited by 44
  5. 2019Accurate, reliable and fast robustness evaluationcited by 43
  6. 2020Scaling Polyhedral Neural Network Verification on GPUscited by 43
  7. 2022The Third International Verification of Neural Networks Competition (VNN-COMP 2022): Summary and Resultscited by 39
  8. 2020Reachable Polyhedral Marching (RPM): A Safety Verification Algorithm for Robotic Systems with Deep Neural Network Componentscited by 36
  9. 2020Abstraction based Output Range Analysis for Neural Networkscited by 34
  10. 2021Statistical inference for individual fairnesscited by 13
  11. 2020Verification of Neural Networks: Enhancing Scalability through Pruningcited by 8
  12. 2020Debona: Decoupled Boundary Network Analysis for Tighter Bounds and Faster Adversarial Robustness Proofscited by 8
  13. 2021Fast BATLLNN: Fast Box Analysis of Two-Level Lattice Neural Networkscited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021Noise Sensitivity-Based Energy Efficient and Robust Adversary Detection in Neural Networks
  2. 2025Confidence-gated training for efficient early-exit neural networks
  3. 2026Fast Adversarial Attacks with Gradient Prediction
  4. 2021Compact and Optimal Deep Learning with Recurrent Parameter Generators
  5. 2025DARD: Dice Adversarial Robustness Distillation against Adversarial Attacks
  6. 2021SparseDNN: Fast Sparse Deep Learning Inference on CPUs
  7. 2022Towards Alternative Techniques for Improving Adversarial Robustness: Analysis of Adversarial Training at a Spectrum of Perturbations
  8. 2026Training Under Challenge: Executable Certificates and Challenge-Closed Optimality for Neural Networks