一句话：在模型组件（head/neck/backbone）层面组装测试输入模型，对汽车深度学习框架做差分测试以发现崩溃与数值不一致缺陷。
汽车深度学习框架为满足实时性与资源约束而优化，但在复杂部署环境下易出现调度内存受限引发的崩溃与内存分配错误等质量问题。现有 DL 框架测试方法生成的模型因缺少多输入/输出张量、多模态数据与多层级特征提取能力而无法部署到自动驾驶系统，导致漏检。Scalpel 在模型组件层面生成测试模型：维护 heads/necks/backbones 组件仓库，经选择、变异与组装生成模型，并将部署成功的模型回填仓库，再在自动驾驶系统中进行差分测试。在 Apollo 中检出 16 个崩溃与 21 个 NaN/不一致缺陷（10 个崩溃获确认），模型生成与缺陷检测效率分别提升 27.44× 与 8.5×；Autoware 中检出 9 个崩溃与 16 个缺陷，展现泛化性。
Deep learning (DL) plays a key role in autonomous driving systems. DL models support perception modules, equipped with tasks such as object detection and sensor fusion. These DL models enable vehicles to process multi-sensor inputs to understand complex surroundings. Deploying DL models in autonomous driving systems faces stringent challenges, including real-time processing, limited computational resources, and strict power constraints. To address these challenges, automotive DL frameworks (e.g., PaddleInference) have emerged to optimize inference efficiency. However, these frameworks encounter unique quality issues due to their more complex deployment environments, such as crashes stemming from limited scheduled memory and incorrect memory allocation. Unfortunately, existing DL framework testing methods fail to detect these quality issues due to the failure in deploying generated test input models, as these models lack three essential capabilities: (1) multi-input/output tensor processing, (2) multi-modal data processing, and (3) multi-level data feature extraction. These capabilities necessitate specialized model components, which existing testing methods neglect during model generation. To bridge this gap, we propose Scalpel, an automotive DL frameworks testing method that generates test input models at the model component level. Scalpel generates models by assembling model components (heads, necks, backbones) to support capabilities required by autonomous driving systems. Specifically, Scalpel maintains and updates a repository of model components, generating test inputs by selecting, mutating, and assembling them. Successfully generated models are added back to enrich the repository. Newly generated models are then deployed within the autonomous driving system to test automotive DL frameworks via differential testing. The experimental results demonstrate that Scalpel outperforms existing methods in both effectiveness and efficiency. In Apollo, Scalpel detects 16 crashes and 21 NaN & inconsistency bugs. All detected bugs have been reported to open-source communities, with 10 crashes confirmed. Scalpel achieves 27.44 × and 8.5 × improvements in model generation efficiency and bug detection efficiency. Additionally, Scalpel detects nine crashes and 16 NaN & inconsistency bugs in Autoware, which shows its excellent generalization.
@inproceedings{abs-2510-21451,
title = {Scalpel: Automotive Deep Learning Framework Testing via Assembling Model Components},
author = {Yinglong Zou and Juan Zhai and Chunrong Fang and An Guo and Jiawei Liu and Zhenyu Chen},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3773242}
}