Differential Zonotopes for Verifying Global Robustness of DNNs

• URL: http://arxiv.org/abs/2606.21282v1
• Date: Fri, 19 Jun 2026 09:58:50 GMT
• Title: Differential Zonotopes for Verifying Global Robustness of DNNs
• Abstract summary: robustness of deep neural networks (DNNs) is critical in security-sensitive applications.<n>We present a novel static analysis technique for verifying the global robustness of DNNs.<n>Our results show that TwoSafe significantly outperforms the state of the art in both precision and scalability.
• Score: 10.969524099140814
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The robustness of deep neural networks (DNNs) is critical in security-sensitive applications, where small input perturbations should not alter model predictions. This property is commonly formalized as local or global robustness: the former considers perturbations around a single input, while the latter -- strictly stronger -- quantifies over all input pairs. While local robustness can be expressed as a safety property, global robustness is a 2-safety property, making it substantially more challenging to verify. We present a novel static analysis technique for verifying the global robustness of DNNs. Our approach is based on differential halo zonotopes, a new abstract domain that extends zonotopes to jointly propagate pairs of perturbed inputs in lock-step while tightly bounding their divergence. In addition, we introduce a symmetric variant of confidence-based global robustness that disregards perturbations leading to differing but low-confidence predictions. This relaxation yields a practically meaningful notion of robustness that applies to a broader class of networks. We implement our approach in a new tool, called TwoSafe, and evaluate it on standard DNN verification benchmarks, including widely deployed models. Our results show that TwoSafe significantly outperforms the state of the art in both precision and scalability, enabling the verification of networks an order of magnitude larger than those handled by prior techniques.

Related papers

• Calibrated Adversarial Sampling: Multi-Armed Bandit-Guided Generalization Against Unforeseen Attacks [10.840475405540458]
  Adversarial training (AT) has emerged as one of the most effective paradigms for enhancing the robustness of Deep Neural Networks (DNNs)<n>We propose an efficient fine-tuning method called Calibrated Adversarial Sampling (CAS) to address these issues.<n>Experiments on benchmark datasets show that CAS achieves superior overall robustness while maintaining high clean accuracy.
  arXiv  Detail & Related papers  (2025-11-15T15:42:40Z)
• Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts [80.32933059529135]
  Test-Time Adaptation (TTA) methods have emerged to adapt to target distributions during inference.<n>We propose Dual Uncertainty Optimization (DUO), the first TTA framework designed to jointly minimize both uncertainties for robust M3OD.<n>In parallel, we design a semantic-aware normal field constraint that preserves geometric coherence in regions with clear semantic cues.
  arXiv  Detail & Related papers  (2025-08-28T07:09:21Z)
• Advancing Neural Network Verification through Hierarchical Safety Abstract Interpretation [52.626086874715284]
  We introduce a novel problem formulation called Abstract DNN-Verification, which verifies a hierarchical structure of unsafe outputs.<n>By leveraging abstract interpretation and reasoning about output reachable sets, our approach enables assessing multiple safety levels during the formal verification process.<n>Our contributions include a theoretical exploration of the relationship between our novel abstract safety formulation and existing approaches.
  arXiv  Detail & Related papers  (2025-05-08T13:29:46Z)
• Hierarchical Uncertainty-Aware Graph Neural Network [3.4498722449655066]
  This work introduces a novel architecture, the Hierarchical Uncertainty-Aware Graph Neural Network (HU-GNN)<n>It unifies multi-scale representation learning, principled uncertainty estimation, and self-supervised embedding diversity within a single end-to-end framework.<n>Specifically, HU-GNN adaptively forms node clusters and estimates uncertainty at multiple structural scales from individual nodes to higher levels.
  arXiv  Detail & Related papers  (2025-04-28T14:22:18Z)
• Scaling #DNN-Verification Tools with Efficient Bound Propagation and Parallel Computing [57.49021927832259]
  Deep Neural Networks (DNNs) are powerful tools that have shown extraordinary results in many scenarios. However, their intricate designs and lack of transparency raise safety concerns when applied in real-world applications. Formal Verification (FV) of DNNs has emerged as a valuable solution to provide provable guarantees on the safety aspect.
  arXiv  Detail & Related papers  (2023-12-10T13:51:25Z)
• Enumerating Safe Regions in Deep Neural Networks with Provable Probabilistic Guarantees [86.1362094580439]
  We introduce the AllDNN-Verification problem: given a safety property and a DNN, enumerate the set of all the regions of the property input domain which are safe. Due to the #P-hardness of the problem, we propose an efficient approximation method called epsilon-ProVe. Our approach exploits a controllable underestimation of the output reachable sets obtained via statistical prediction of tolerance limits.
  arXiv  Detail & Related papers  (2023-08-18T22:30:35Z)
• Generalizability of Adversarial Robustness Under Distribution Shifts [57.767152566761304]
  We take a first step towards investigating the interplay between empirical and certified adversarial robustness on one hand and domain generalization on another. We train robust models on multiple domains and evaluate their accuracy and robustness on an unseen domain. We extend our study to cover a real-world medical application, in which adversarial augmentation significantly boosts the generalization of robustness with minimal effect on clean data accuracy.
  arXiv  Detail & Related papers  (2022-09-29T18:25:48Z)
• Efficient Global Robustness Certification of Neural Networks via Interleaving Twin-Network Encoding [8.173681464694651]
  We formulate the global robustness certification for neural networks with ReLU activation functions as a mixed-integer linear programming (MILP) problem. Our approach includes a novel interleaving twin-network encoding scheme, where two copies of the neural network are encoded side-by-side. A case study of closed-loop control safety verification is conducted, and demonstrates the importance and practicality of our approach.
  arXiv  Detail & Related papers  (2022-03-26T19:23:37Z)
• Uncertainty-Aware Deep Calibrated Salient Object Detection [74.58153220370527]
  Existing deep neural network based salient object detection (SOD) methods mainly focus on pursuing high network accuracy. These methods overlook the gap between network accuracy and prediction confidence, known as the confidence uncalibration problem. We introduce an uncertaintyaware deep SOD network, and propose two strategies to prevent deep SOD networks from being overconfident.
  arXiv  Detail & Related papers  (2020-12-10T23:28:36Z)

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.