HyperNet-Adaptation for Diffusion-Based Test Case Generation

TL;DR

HyNeA is a novel hypernetwork-based diffusion model method that enables targeted, dataset-free generation of realistic failure cases for testing deep learning systems efficiently and with high controllability.

Contribution

The paper introduces HyNeA, a hypernetwork-driven diffusion testing framework that allows direct control and instance-level tuning without dataset reliance or architecture-specific conditioning.

Findings

HyNeA improves controllability over diffusion-based test generation.

HyNeA generates diverse, realistic failure cases efficiently.

HyNeA generalizes to failure domains without labeled data.

Abstract

The increasing deployment of deep learning systems requires systematic evaluation of their reliability in real-world scenarios. Traditional gradient-based adversarial attacks introduce small perturbations that rarely correspond to realistic failures and mainly assess robustness rather than functional behavior. Generative test generation methods offer an alternative but are often limited to simple datasets or constrained input domains. Although diffusion models enable high-fidelity image synthesis, their computational cost and limited controllability restrict their applicability to large-scale testing. We present HyNeA, a generative testing method that enables direct and efficient control over diffusion-based generation. HyNeA provides dataset-free controllability through hypernetworks, allowing targeted manipulation of the generative process without relying on architecture-specific conditioning mechanisms or dataset-driven adaptations such as fine-tuning. HyNeA employs a distinct training strategy that supports instance-level tuning to identify failure-inducing test cases without requiring datasets that explicitly contain examples of similar failures. This approach enables the targeted generation of realistic failure cases at substantially lower computational cost than search-based methods. Experimental results show that HyNeA improves controllability and test diversity compared to existing generative test generators and generalizes to domains where failure-labeled training data is unavailable.