Target Model Agnostic Adversarial Attacks with Query Budgets on Language Understanding Models

arxiv(2021)

引用 2|浏览17
暂无评分
摘要
Despite significant improvements in natural language understanding models with the advent of models like BERT and XLNet, these neural-network based classifiers are vulnerable to blackbox adversarial attacks, where the attacker is only allowed to query the target model outputs. We add two more realistic restrictions on the attack methods, namely limiting the number of queries allowed (query budget) and crafting attacks that easily transfer across different pre-trained models (transferability), which render previous attack models impractical and ineffective. Here, we propose a target model agnostic adversarial attack method with a high degree of attack transferability across the attacked models. Our empirical studies show that in comparison to baseline methods, our method generates highly transferable adversarial sentences under the restriction of limited query budgets.
更多
查看译文
关键词
language understanding models,query budgets
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要