Adversarial Defense on Harmony: Reverse Attack for Robust AI Models Against Adversarial Attacks

Adversarial Defense on Harmony: Reverse Attack for Robust AI Models Against Adversarial Attacks

Deep neural networks (DNNs) are crucial in safety-critical applications but vulnerable to adversarial attacks, where subtle perturbations cause misclassification. Existing defense mechanisms struggle with small perturbations and face accuracy-robustness trade-offs. This study introduces the &#x2...

Descrizione completa

Dettagli Bibliografici
Autori principali: Yebon Kim, Jinhyo Jung, Hyunjun Kim, Hwisoo So, Yohan Ko, Aviral Shrivastava, Kyoungwoo Lee, Uiwon Hwang
Natura: Articolo
Lingua:English
Pubblicazione: IEEE 2024-01-01
Serie:IEEE Access
Soggetti:
Deep neural networks
adversarial attacks and defenses
security
reliability
Accesso online:https://ieeexplore.ieee.org/document/10766602/

Accesso online

https://ieeexplore.ieee.org/document/10766602/

Documenti analoghi