Invisible Threats in the Data: A Study on Data Poisoning Attacks in Deep Generative Models

Deep Generative Models (DGMs), as a state-of-the-art technology in the field of artificial intelligence, find extensive applications across various domains. However, their security concerns have increasingly gained prominence, particularly with regard to invisible backdoor attacks. Currently, most b...

وصف كامل

التفاصيل البيبلوغرافية
الحاوية / القاعدة:Applied Sciences
المؤلفون الرئيسيون: Ziying Yang, Jie Zhang, Wei Wang, Huan Li
التنسيق: مقال
اللغة:الإنجليزية
منشور في: MDPI AG 2024-09-01
الموضوعات:
backdoor attack
deep generative models
data poisoning
invisible trigger
الوصول للمادة أونلاين:https://www.mdpi.com/2076-3417/14/19/8742

الانترنت

https://www.mdpi.com/2076-3417/14/19/8742

مواد مشابهة