Adversarial Attacks in Underwater Acoustic Target Recognition with Deep Learning Models

Deep learning models can produce unstable results by introducing imperceptible perturbations that are difficult for humans to recognize. This can have a significant impact on the accuracy and security of deep learning applications due to their poorly understood interpretability. As a field critical...

وصف كامل

التفاصيل البيبلوغرافية
الحاوية / القاعدة:Remote Sensing
المؤلفون الرئيسيون: Sheng Feng, Xiaoqian Zhu, Shuqing Ma, Qiang Lan
التنسيق: مقال
اللغة:الإنجليزية
منشور في: MDPI AG 2023-11-01
الموضوعات:
model security
imperceptible perturbations
model interpretability
Mel-spectrogram
الوصول للمادة أونلاين:https://www.mdpi.com/2072-4292/15/22/5386

الانترنت

https://www.mdpi.com/2072-4292/15/22/5386

مواد مشابهة