Towards Precise Observations of Neural Model Robustness in Classification

April 25, 2024 Β· Declared Dead Β· πŸ› 2024 IEEE/ACM 46th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Wenchuan Mu, Kwan Hui Lim arXiv ID 2404.16457 Category cs.SE: Software Engineering Cross-listed cs.AI Citations 1 Venue 2024 IEEE/ACM 46th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) Last Checked 4 months ago
Abstract
In deep learning applications, robustness measures the ability of neural models that handle slight changes in input data, which could lead to potential safety hazards, especially in safety-critical applications. Pre-deployment assessment of model robustness is essential, but existing methods often suffer from either high costs or imprecise results. To enhance safety in real-world scenarios, metrics that effectively capture the model's robustness are needed. To address this issue, we compare the rigour and usage conditions of various assessment methods based on different definitions. Then, we propose a straightforward and practical metric utilizing hypothesis testing for probabilistic robustness and have integrated it into the TorchAttacks library. Through a comparative analysis of diverse robustness assessment methods, our approach contributes to a deeper understanding of model robustness in safety-critical applications.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Software Engineering

Died the same way β€” πŸ‘» Ghosted