arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.01017cs.LGcs.CRstat.ML
收藏

深度学习防御动态风险评估的对抗性示例

Deep Learning Defenses Against Adversarial Examples for Dynamic Risk Assessment

Vicomtech Foundation(维康特奇基金会);Basque Research and Technology Alliance(巴斯克研究与技术联盟)

Xabier Echeberria-Barrio, Amaia Gil-Lerchundi, Ines Goicoechea-Telleria, Raul Orduna-Urrutia

摘要:

深度神经网络最初是在几十年前开发的,但直到最近,由于其计算能力的要求,它们才开始被广泛使用。从那时起,它们越来越多地应用于许多领域,并取得了深远的进步。更重要的是,它们已被用于关键事项,例如在医疗程序或自动驾驶中做出决策,其中风险管理至关重要。在这些领域的诊断或决策中的任何错误都可能导致严重事故,甚至死亡。这是令人关注的,因为已经多次报道攻击这种类型的模型是直接的。因此,必须对这些攻击进行研究,以评估其风险,并开发防御措施,使模型更加强大。在这项工作中,选择了最广为人知的攻击(对抗攻击),并对其实施了几种防御(即对抗训练,降维和预测相似性)。所获得的结果使得模型在保持相似精度的同时更加鲁棒。这个想法是使用乳腺癌数据集和VGG 16和密集神经网络模型开发的,但解决方案可以应用于其他领域的数据集和不同的卷积和密集深度神经网络模型。

英文摘要:

Deep Neural Networks were first developed decades ago, but it was not until recently that they started being extensively used, due to their computing power requirements. Since then, they are increasingly being applied to many fields and have undergone far-reaching advancements. More importantly, they have been utilized for critical matters, such as making decisions in healthcare procedures or autonomous driving, where risk management is crucial. Any mistakes in the diagnostics or decision-making in these fields could entail grave accidents, and even death. This is preoccupying, because it has been repeatedly reported that it is straightforward to attack this type of models. Thus, these attacks must be studied to be able to assess their risk, and defenses need to be developed to make models more robust. For this work, the most widely known attack was selected (adversarial attack) and several defenses were implemented against it (i.e. adversarial training, dimensionality reduc tion and prediction similarity). The obtained outcomes make the model more robust while keeping a similar accuracy. The idea was developed using a breast cancer dataset and a VGG16 and dense neural network model, but the solutions could be applied to datasets from other areas and different convolutional and dense deep neural network models.

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。

↑