Masking and purifying inputs for blocking textual adversarial attacks.
Huan ZhangZhaoquan GuHao TanLe WangZiqi ZhuYushun XieJianxin LiPublished in: Inf. Sci. (2023)
Keyphrases
- countermeasures
- record linkage
- keywords
- denial of service attacks
- multimedia
- attack detection
- human visual system
- watermarking scheme
- security protocols
- chosen plaintext
- information systems
- malicious attacks
- textual features
- cyber attacks
- computer security
- security mechanisms
- watermarking algorithm
- textual information
- high frequency
- digital images
- multi agent