arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.10250cs.LGcs.CRstat.ML
收藏

模型集成的联合对抗鲁棒性证明

Certifying Joint Adversarial Robustness for Model Ensembles

University of Virginia(弗吉尼亚大学)

Mainuddin Ahmad Jonas, David Evans

摘要:

深度神经网络(DNN)通常容易受到对抗性样本的攻击。一些提出的防御方法部署了一个模型集合,希望尽管单个模型可能容易受到攻击,但对手将无法找到成功对抗集合的对抗性样本。根据集成的使用方式,攻击者可能需要找到一个对抗性的例子,成功地对抗集成中的所有或大多数模型。集成防御对强大对手的有效性取决于集成中模型的脆弱性空间是不相交的。我们认为,联合脆弱性的合奏模型,并提出了一种新的技术,用于证明合奏的联合鲁棒性,建立在以前的工作单模型的鲁棒性认证。我们评估了各种模型集成的鲁棒性,包括使用成本敏感鲁棒性训练的模型,以提高对集成模型作为对抗性示例防御的潜在有效性的理解。

英文摘要:

Deep Neural Networks (DNNs) are often vulnerable to adversarial examples.Several proposed defenses deploy an ensemble of models with the hope that, although the individual models may be vulnerable, an adversary will not be able to find an adversarial example that succeeds against the ensemble. Depending on how the ensemble is used, an attacker may need to find a single adversarial example that succeeds against all, or a majority, of the models in the ensemble. The effectiveness of ensemble defenses against strong adversaries depends on the vulnerability spaces of models in the ensemble being disjoint. We consider the joint vulnerability of an ensemble of models, and propose a novel technique for certifying the joint robustness of ensembles, building upon prior works on single-model robustness certification. We evaluate the robustness of various models ensembles, including models trained using cost-sensitive robustness to be diverse, to improve understanding of the potential effectiveness of ensemble models as a defense against adversarial examples.

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。

↑