Simulator-based Explanation and Debugging of Hazard-triggering Events in DNN-based Safety-critical Systems
When Deep Neural Networks (DNNs) are used in safety-critical systems, engineers should determine the safety risks associated with failures (i.e., erroneous outputs) observed during testing. For DNNs processing images, engineers visually inspect all failure-inducing images to determine common characteristics among them. Such characteristics correspond to hazard-triggering events (e.g., low illumination) that are essential inputs for safety analysis. Though informative, such activity is expensive and error prone.
To support such safety analysis practices, we propose Simulator-based Explanations for DNN failurEs (SEDE), a technique that generates readable descriptions for commonalities in failure-inducing, real-world images and improves the DNN through effective retraining. SEDE leverages the availability of simulators, which are commonly used for cyber-physical systems. It relies on genetic algorithms to drive simulators toward the generation of images that are similar to failure-inducing, real-world images in the test set; it then employs rule learning algorithms to derive expressions that capture commonalities in terms of simulator parameter values. The derived expressions are then used to generate additional images to retrain and improve the DNN.
With DNNs performing in-car sensing tasks, SEDE successfully characterized hazard-triggering events leading to a DNN accuracy drop. Also, SEDE enabled retraining leading to significant improvements in DNN accuracy, up to 18 percentage points.
|Simulator-based Explanation and Debugging of Hazard-triggering Events in DNN-based Safety-critical Systems (3569935.pdf)||2.64MiB|
Tue 12 SepDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
13:30 - 15:00
|ATOM: Automated Black-Box Testing of Multi-Label Image Classification Systems|
Shengyou Hu Nanjing University, Huayao Wu Nanjing University, Peng Wang Fudan University, Jing Chang Guangdong OPPO Mobile Telecommunications Corp.,Ltd., Yongjun Tu Guangdong OPPO Mobile Telecommunications Corp.,Ltd., Xiu Jiang Guangdong OPPO Mobile Telecommunications Corp.,Ltd., Xintao Niu Nanjing University, Changhai Nie Nanjing UniversityPre-print Media Attached File Attached
|Automating Bias Testing of LLMs|
Sergio Morales Universitat Oberta de Catalunya, Robert Clarisó Universitat Oberta de Catalunya, Jordi Cabot Luxembourg Institute of Science and TechnologyPre-print File Attached
|MUTEN: Mutant-Based Ensembles for Boosting Gradient-Based Adversarial Attack|
Qiang Hu University of Luxembourg, Yuejun GUo Luxembourg Institute of Science and Technology, Maxime Cordy University of Luxembourg, Luxembourg, Mike Papadakis University of Luxembourg, Luxembourg, Yves Le Traon University of Luxembourg, LuxembourgFile Attached
|Generative Model-Based Testing on Decision-Making Policies|
Zhuo Li Kyushu University, Xiongfei Wu Kyushu University, Derui Zhu Technical University of Munich, Mingfei Cheng Singapore Management University, Siyuan Chen Kyushu University, Fuyuan Zhang Kyushu University, Xiaofei Xie Singapore Management University, Lei Ma University of Alberta, Jianjun Zhao Kyushu UniversityFile Attached
|Simulator-based Explanation and Debugging of Hazard-triggering Events in DNN-based Safety-critical Systems|
Hazem FAHMY University of Luxembourg, Fabrizio Pastore University of Luxembourg, Lionel Briand University of Luxembourg; University of Ottawa, Thomas Stifter IEE S.A.Link to publication DOI Pre-print File Attached
|Are We Ready to Embrace Generative AI for Software Q&A?|
Bowen Xu North Carolina State University, Thanh-Dat Nguyen University of Melbourne, Le-Cong Thanh The University of Melbourne, Thong Hoang CSIRO's Data61, Jiakun Liu Singapore Management University, Kisub Kim Singapore Management University, Singapore, Chen GONG University of Virginia, Changan Niu Software Institute, Nanjing University, Chenyu Wang Singapore Management University, Xuan-Bach D. Le University of Melbourne, David Lo Singapore Management University