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 1908.07000cs.CR
收藏

混合批处理攻击:在有限时间内发现黑盒对抗示例

Hybrid Batch Attacks: Finding Black-box Adversarial Examples with Limited Queries

Fnu Suya, Jianfeng Chi, David Evans, Yuan Tian

摘要:

我们在黑盒设置中研究对抗性示例,其中对手只能访问目标模型的API,并且每个查询都是昂贵的。黑盒对抗性示例的先前工作遵循两种主要策略之一:(1)转移攻击使用局部模型上的白盒攻击来寻找转移到目标模型的候选对抗性示例,以及(2)基于优化的攻击使用对目标模型的查询并应用优化技术来搜索对抗性示例。我们提出了结合这两种策略的混合攻击,使用来自本地模型的候选对抗示例作为基于优化的攻击的起点,并使用在基于优化的攻击中学习的标签来调整本地模型以找到转移候选者。我们在MNIST、CIFAR10和ImageNet数据集上实证证明,我们的混合攻击策略降低了成本,提高了成功率。我们还引入了一种种子优先级策略,使攻击者能够将资源集中在最有前途的种子上。将混合攻击与我们的种子优先级策略相结合,可以实现批量攻击,只需少量查询就可以可靠地找到对抗性示例。

英文摘要:

We study adversarial examples in a black-box setting where the adversary only has API access to the target model and each query is expensive. Prior work on black-box adversarial examples follows one of two main strategies: (1) transfer attacks use white-box attacks on local models to find candidate adversarial examples that transfer to the target model, and (2) optimization-based attacks use queries to the target model and apply optimization techniques to search for adversarial examples. We propose hybrid attacks that combine both strategies, using candidate adversarial examples from local models as starting points for optimization-based attacks and using labels learned in optimization-based attacks to tune local models for finding transfer candidates. We empirically demonstrate on the MNIST, CIFAR10, and ImageNet datasets that our hybrid attack strategy reduces cost and improves success rates. We also introduce a seed prioritization strategy which enables attackers to focus their resources on the most promising seeds. Combining hybrid attacks with our seed prioritization strategy enables batch attacks that can reliably find adversarial examples with only a handful of queries.

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。

↑