一句话：提出面向图像DNN的实体级正确性性质框架，用目标检测自动生成领域特定性质以揭示系统失败。
图像DNN广泛用于安全关键任务，但其正确性性质通常定义在像素级、覆盖整个输入，因而只能暴露传感器噪声或对抗攻击等系统失败，无法表达领域特定实体及其语义变化。为克服该局限，论文设想基于图像中可能出现的实体来指定性质，并构建初始框架：利用目标检测模型识别实体，再根据实体特征自动生成领域特定、实体级的性质，以适配不同V&V客户端。可行性研究给出初步证据，表明这类性质能发现有趣的系统失败，例如肤色变化可改变性别分类网络的输出；最后分析框架实现该愿景的潜力并讨论未来方向。
Deep Neural Networks (DNNs) that process images are being widely used for many safety-critical tasks, from autonomous vehicles to medical diagnosis. Currently, DNN correctness properties are defined at the pixel level over the entire input. Such properties are useful to expose system failures related to sensor noise or adversarial attacks, but they cannot capture features that are relevant to domain-specific entities and reflect richer types of behaviors. To overcome this limitation, we envision the specification of properties based on the entities that may be present in image input, capturing their semantics and how they change. Creating such properties today is difficult as it requires determining where the entities appear in images, defining how each entity can change, and writing a specification that is compatible with each particular V&V client. We introduce an initial framework structured around those challenges to assist in the generation of Domain-specific Entity-based properties automatically by leveraging object detection models to identify entities in images and creating properties based on entity features. Our feasibility study provides initial evidence that the new properties can uncover interesting system failures, such as changes in skin color can modify the output of a gender classification network. We conclude by analyzing the framework potential to implement the vision and by outlining directions for future work.
@inproceedings{ToledoSED23,
title = {Deeper Notions of Correctness in Image-Based DNNs: Lifting Properties from Pixel to Entities},
author = {Felipe Toledo and David Shriver and Sebastian Elbaum and Matthew B. Dwyer},
booktitle = {FSE},
year = {2023},
doi = {10.1145/3611643.3613079}
}