69一区二三区好的精华液,中文字幕无码av波多野吉衣,亚洲精品久久久久久无码色欲四季,日本不卡高字幕在线2019

One paper has been accepted by EMNLP2024.

Our paper entitled "Adaptive Immune-based Sound-Shape code Substitution for Adversarial Chinese Text Attacks" has been accepted by EMNLP2024.

Adaptive Immune-based Sound-Shape code Substitution for Adversarial Chinese Text Attacks

Ao Wang, Xinghao Yang, Chen Li, Bao-di Liu, Weifeng Liu

Adversarial textual examples reveal the vulnerability of natural language processing (NLP) models. Most existing text attack methods are designed for English text, while the robust implementation of the second popular language, i.e., Chinese with 1 billion users, is greatly underestimated. Although several Chinese attack methods have been presented, they either directly transfer from English attacks or adopt simple greedy search to optimize the attack priority, usually leading to unnatural sentences. To address these issues, we propose an adaptive Immune-based Sound-Shape Code (ISSC) algorithm for adversarial Chinese text attacks. Firstly, we leverage the Sound-Shape code to generate natural substitutions, which comprehensively integrate multiple Chinese features. Secondly, we employ adaptive immune algorithm (IA) to determine the replacement order, which can reduce the duplication of population to improve the search ability. Extensive experimental results validate the superiority of our ISSC in producing high-quality Chinese adversarial texts.

 


登錄用戶可以查看和發(fā)表評(píng)論, 請(qǐng)前往  登錄 或  注冊(cè)
SCHOLAT.com 學(xué)者網(wǎng)
免責(zé)聲明 | 關(guān)于我們 | 用戶反饋
聯(lián)系我們:
主站蜘蛛池模板: 云梦县| 张家界市| 南昌市| 浙江省| 南京市| 进贤县| 图片| 华蓥市| 辽阳市| 珠海市| 巩留县| 长沙市| 都昌县| 崇州市| 时尚| 高台县| 呼玛县| 绥芬河市| 太康县| 新余市| 普兰店市| 太仆寺旗| 玉龙| 吉木萨尔县| 托克逊县| 赣榆县| 乌鲁木齐市| 广宗县| 察雅县| 神木县| 太康县| 利辛县| 咸阳市| 晴隆县| 宜良县| 洛阳市| 中西区| 溧阳市| 英吉沙县| 克东县| 通许县|