# Robustness Certification of Generative Models

arXiv: https://arxiv.org/abs/2004.14756 · HTML: https://mlsanity.com/paper/2004.14756/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2020.

## Built on by (most cited first, 19 of 19)

- [Marabou 2.0: A Versatile Formal Analyzer of Neural Networks](https://mlsanity.com/paper/2401.14461/) (2024)
- [Verification of Image-based Neural Network Controllers Using Generative Models](https://mlsanity.com/paper/2105.07091/) (2021)
- [Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications](https://mlsanity.com/paper/2102.09479/) (2021)
- [Latent Space Smoothing for Individually Fair Representations](https://mlsanity.com/paper/2111.13650/) (2021)
- [From Robustness to Explainability and Back Again](https://mlsanity.com/paper/2306.03048/) (2023)
- [Certifying Counterfactual Bias in LLMs](https://mlsanity.com/paper/2405.18780/) (2024)
- [Precise and Generalized Robustness Certification for Neural Networks](https://mlsanity.com/paper/2306.06747/) (2023)
- [ZoPE: A Fast Optimizer for ReLU Networks with Low-Dimensional Inputs](https://mlsanity.com/paper/2106.05325/) (2021)
- [Verification of Neural Networks against Convolutional Perturbations via Parameterised Kernels](https://mlsanity.com/paper/2411.04594/) (2024)
- [Verifying Attention Robustness of Deep Neural Networks against Semantic Perturbations](https://mlsanity.com/paper/2207.05902/) (2022)
- [Mathematical Algorithm Design for Deep Learning under Societal and Judicial Constraints: The Algorithmic Transparency Requirement](https://mlsanity.com/paper/2401.10310/) (2024)
- [Certifying Knowledge Comprehension in LLMs](https://mlsanity.com/paper/2402.15929/) (2024)
- [VeriFlow: Modeling Distributions for Neural Network Verification](https://mlsanity.com/paper/2406.14265/) (2024)
- [Semantic Robustness Certification for Vision-Language Models](https://mlsanity.com/paper/2606.18839/) (2026)
- [Probabilistic ML Verification via Weighted Model Integration](https://mlsanity.com/paper/2402.04892/) (2024)
- [Learning from Uncertain Data: From Possible Worlds to Possible Models](https://mlsanity.com/paper/2405.18549/) (2024)
- [Specification Generation for Neural Networks in Systems](https://mlsanity.com/paper/2412.03028/) (2024)
- [Towards Compact and Robust DNNs via Compression-aware Sharpness Minimization](https://mlsanity.com/paper/2601.20301/) (2026)
- [Certified Training for Convolutional Perturbations](https://mlsanity.com/paper/2607.18195/) (2026)

## Abstract (arXiv)

Generative neural networks can be used to specify continuous transformations between images via latent-space interpolation. However, certifying that all images captured by the resulting path in the image manifold satisfy a given property can be very challenging. This is because this set is highly non-convex, thwarting existing scalable robustness analysis methods, which are often based on convex relaxations. We present ApproxLine, a scalable certification method that successfully verifies non-trivial specifications involving generative models and classifiers. ApproxLine can provide both sound deterministic and probabilistic guarantees, by capturing either infinite non-convex sets of neural network activation vectors or distributions over such sets. We show that ApproxLine is practically useful and can verify interesting interpolations in the networks latent space.