arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.01806cs.CLcs.AI
收藏

HQA-Attack:面向文本的高质量黑盒硬标签对抗攻击

HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text

Dalian University of Technology(大连理工大学);Peking University(北京大学);The Pennsylvania State University(宾夕法尼亚州立大学);Zhejiang Lab(之江实验室)

Han Liu, Zhi Xu, Xiaotong Zhang, Feng Zhang, Fenglong Ma, Hongyang Chen, Hong Yu, Xianchao Zhang

AI总结:

提出HQA-Attack框架,通过替换回原始词和同义词优化,在黑盒硬标签场景下生成高语义相似度、低扰动率的文本对抗样本,显著优于现有方法。

摘要:

文本上的黑盒硬标签对抗攻击是一项实用且具有挑战性的任务,因为文本数据空间本质上是离散且不可微的,并且只能访问预测标签。对此问题的研究仍处于萌芽阶段,可用的方法很少。然而,现有方法依赖于复杂的启发式算法或不可靠的梯度估计策略,这些方法可能陷入局部最优,并且不可避免地消耗大量查询,因此难以在有限的查询预算内生成具有高语义相似性和低扰动率的令人满意的对抗样本。为了缓解上述问题,我们提出了一个简单而有效的框架,用于在黑盒硬标签攻击场景下生成高质量的文本对抗样本,名为HQA-Attack。具体来说,在随机初始化一个对抗样本后,HQA-Attack首先尽可能多地替换回原始单词,从而缩小扰动率。然后,它利用剩余被修改单词的同义词集,以能够同时提高语义相似性和满足对抗条件的方向进一步优化对抗样本。此外,在优化过程中,它为每个被修改的单词搜索一个过渡同义词,从而避免遍历整个同义词集,并在一定程度上减少查询数量。在五个文本分类数据集、三个自然语言推理数据集和两个真实世界API上的大量实验结果表明,所提出的HQA-Attack方法显著优于其他强基线。

英文摘要:

Black-box hard-label adversarial attack on text is a practical and challenging task, as the text data space is inherently discrete and non-differentiable, and only the predicted label is accessible. Research on this problem is still in the embryonic stage and only a few methods are available. Nevertheless, existing methods rely on the complex heuristic algorithm or unreliable gradient estimation strategy, which probably fall into the local optimum and inevitably consume numerous queries, thus are difficult to craft satisfactory adversarial examples with high semantic similarity and low perturbation rate in a limited query budget. To alleviate above issues, we propose a simple yet effective framework to generate high quality textual adversarial examples under the black-box hard-label attack scenarios, named HQA-Attack. Specifically, after initializing an adversarial example randomly, HQA-attack first constantly substitutes original words back as many as possible, thus shrinking the perturbation rate. Then it leverages the synonym set of the remaining changed words to further optimize the adversarial example with the direction which can improve the semantic similarity and satisfy the adversarial condition simultaneously. In addition, during the optimizing procedure, it searches a transition synonym word for each changed word, thus avoiding traversing the whole synonym set and reducing the query number to some extent. Extensive experimental results on five text classification datasets, three natural language inference datasets and two real-world APIs have shown that the proposed HQA-Attack method outperforms other strong baselines significantly.

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。

↑