Text Select-Backdoor: Selective Backdoor Attack for Text Recognition Systems

Deep neural networks exhibit excellent image, voice, text, and pattern recognition performance. However, they are vulnerable to adversarial and backdoor attacks. In a backdoor attack, the target model identifies input data unless it contains a specific trigger, at which point it mistakenly recognize...

Descrizione completa

Dettagli Bibliografici

Autori principali:	Hyun Kwon, Jang-Woon Baek
Natura:	Artigo
Lingua:	Inglês
Pubblicazione:	IEEE 2024-01-01
Serie:	IEEE Access
Soggetti:	Deep neural network text domain machine-learning security backdoor attack
Accesso online:	https://ieeexplore.ieee.org/document/10741518/
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!