Thu 7 Dec 2023 14:15 - 14:30 at Golden Gate C2 - Machine Learning V Chair(s): Prem Devanbu

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 uncover system faults related to sensor noise or adversarial attacks. However, those properties cannot capture features that are relevant to domain-specific entities and reflect richer types of behaviors. To overcome this limitation, we envision the ability to specify properties based on the entities that may be present in image input, capturing their semantics and how they change. Creating such properties today is a difficult task that 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 \longnewproperties 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 detect interesting system faults, such as changes in skin color can modify the output of a gender classification network. We conclude by analyzing the potential of the framework to address the gaps in our vision and by outlining possible directions for future work.

Thu 7 Dec

Displayed time zone: Pacific Time (US & Canada) change

14:00 - 15:30
Machine Learning VResearch Papers / Ideas, Visions and Reflections / Journal First at Golden Gate C2
Chair(s): Prem Devanbu University of California at Davis
14:00
15m
Talk
LExecutor: Learning-Guided Execution
Research Papers
Beatriz Souza Universit├Ąt Stuttgart, Michael Pradel University of Stuttgart
Media Attached
14:15
15m
Talk
Deeper Notions of Correctness in Image-based DNNs: Lifting Properties from Pixel to Entities
Ideas, Visions and Reflections
Felipe Toledo , David Shriver University of Virginia, Sebastian Elbaum University of Virginia, Matthew B Dwyer University of Virginia
Link to publication DOI Pre-print Media Attached
14:30
15m
Talk
Software Architecture Recovery with Information Fusion
Research Papers
Yiran Zhang Nanyang Technological University, Zhengzi Xu Nanyang Technological University, Chengwei Liu Nanyang Technological University, Hongxu Chen Huawei Technologies Co., Ltd., Sun Jianwen Huawei Technologies Co., Ltd, Dong Qiu Huawei Technologies Co., Ltd, Yang Liu Nanyang Technological University
Media Attached
14:45
15m
Talk
What Kinds of Contracts Do ML APIs Need?
Journal First
Samantha Syeda Khairunnesa Bradley University, Shibbir Ahmed Dept. of Computer Science, Iowa State University, Sayem Mohammad Imtiaz Iowa State University, Hridesh Rajan Dept. of Computer Science, Iowa State University, Gary T. Leavens University of Central Florida
Media Attached
15:00
15m
Talk
Evaluating Transfer Learning for Simplifying GitHub READMEs
Research Papers
Haoyu Gao The University of Melbourne, Christoph Treude University of Melbourne, Mansooreh Zahedi The Univeristy of Melbourne
Pre-print Media Attached
15:15
15m
Talk
[Remote] CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models
Research Papers
Zhensu Sun Singapore Management University, Xiaoning Du Monash University, Australia, Fu Song State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, and University of Chinese Academy of Sciences Beijing, China, Li Li Beihang University
Pre-print Media Attached