14 citations · 45 across the 14 of their papers we have counts for
6 papers · 1 filter
VoteTRANS: Detecting Adversarial Text without Training by Voting on Hard Labels of Transformations
Hoang-Quoc Nguyen-Son, Seira Hidano, Kazuhide Fukushima +2
Adversarial attacks reveal serious flaws in deep learning models. More dangerously, these attacks preserve the original meaning and escape human recognition. Existing methods for d…
Text Revealer: Private Text Reconstruction via Model Inversion Attacks against Transformers
Ruisi Zhang, Seira Hidano, Farinaz Koushanfar
Text classification has become widely used in various natural language processing applications like sentiment analysis. Current applications often use large transformer-based langu…
SEPP: Similarity Estimation of Predicted Probabilities for Defending and Detecting Adversarial Text
Hoang-Quoc Nguyen-Son, Seira Hidano, Kazuhide Fukushima +1
There are two cases describing how a classifier processes input text, namely, misclassification and correct classification. In terms of misclassified texts, a classifier handles th…
Identifying Adversarial Sentences by Analyzing Text Complexity
Hoang-Quoc Nguyen-Son, Tran Phuong Thao, Seira Hidano +1
Attackers create adversarial text to deceive both human perception and the current AI systems to perform malicious purposes such as spam product reviews and fake political posts. W…
Detecting Machine-Translated Text using Back Translation
Hoang-Quoc Nguyen-Son, Tran Phuong Thao, Seira Hidano +1
Machine-translated text plays a crucial role in the communication of people using different languages. However, adversaries can use such text for malicious purposes such as plagiar…
Detecting Machine-Translated Paragraphs by Matching Similar Words
Hoang-Quoc Nguyen-Son, Tran Phuong Thao, Seira Hidano +1
Machine-translated text plays an important role in modern life by smoothing communication from various communities using different languages. However, unnatural translation may lea…