دورية أكاديمية
PRADA: Practical Black-box Adversarial Attacks against Neural Ranking Models.
العنوان: | PRADA: Practical Black-box Adversarial Attacks against Neural Ranking Models. |
---|---|
المؤلفون: | CHEN WU, RUQING ZHANG, JIAFENG GUO, DE RIJKE, MAARTEN, YIXING FAN, XUEQI CHENG |
المصدر: | ACM Transactions on Information Systems; Oct2023, Vol. 41 Issue 4, p1-27, 27p |
مستخلص: | The article's focus lies in examining the vulnerability of neural ranking models (NRMs) to adversarial attacks, particularly emphasizing the Word Substitution Ranking Attack (WSRA) task, aiming to enhance a target document's ranking by subtly altering its text. It covers topics such as proposing a novel PRADA method for generating adversarial examples, conducting experiments on web search datasets, and highlighting the importance of identifying NRM vulnerabilities to enhance model robustness. |
قاعدة البيانات: | Complementary Index |
كن أول من يترك تعليقا!