arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.02695cs.CLcs.AIcs.CRcs.LG
收藏

利用类别概率进行黑盒句子级攻击

Exploiting Class Probabilities for Black-box Sentence-level Attacks

Arizona State University(亚利桑那州立大学)

Raha Moraffah, Huan Liu

AI总结:

本文提出一种利用类别概率反馈的黑盒句子级攻击新算法,克服了现有方法仅用标签或无反馈的局限,并通过多分类器和基准数据集上的广泛评估验证了其有效性。

摘要:

句子级攻击构造与正确分类句子同义但被文本分类器错误分类的对抗性句子。在黑盒设置下,分类器只能通过其对查询输入的反馈来访问,而这种反馈主要以类别概率的形式提供。尽管利用类别概率可以产生更强的攻击,但由于将其用于句子级攻击存在诸多挑战,现有攻击要么不使用任何反馈,要么仅使用类别标签。为克服这些挑战,我们开发了一种利用类别概率进行黑盒句子级攻击的新算法,研究了使用类别概率对攻击成功率的影响,并考察了黑盒句子级攻击使用类别概率是否值得或实用的问题。我们在多个分类器和基准数据集上对我们的攻击与基线方法进行了广泛评估。

英文摘要:

Sentence-level attacks craft adversarial sentences that are synonymous with correctly-classified sentences but are misclassified by the text classifiers. Under the black-box setting, classifiers are only accessible through their feedback to queried inputs, which is predominately available in the form of class probabilities. Even though utilizing class probabilities results in stronger attacks, due to the challenges of using them for sentence-level attacks, existing attacks use either no feedback or only the class labels. Overcoming the challenges, we develop a novel algorithm that uses class probabilities for black-box sentence-level attacks, investigate the effectiveness of using class probabilities on the attack's success, and examine the question if it is worthy or practical to use class probabilities by black-box sentence-level attacks. We conduct extensive evaluations of our attack comparing with the baselines across various classifiers and benchmark datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑