arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.06166cs.LGcs.CRcs.GT
收藏

用于对抗攻击与防御的博弈论

Game Theory for Adversarial Attacks and Defenses

Indian Institute of Technology Bhubaneswar(印度理工学院布巴内斯瓦尔分校)

Shorya Sharma

AI总结:

本研究应用博弈论防御对抗攻击,通过随机初始化、随机激活剪枝和超分辨率三种方法提升深度神经网络的鲁棒性。

摘要:

对抗攻击通过对数据集样本施加微小但蓄意的最坏情况扰动来生成对抗输入,这导致即使是最先进的深度神经网络也会以高置信度输出错误答案。因此,开发了一些对抗防御技术以提高模型的安全性和鲁棒性,避免其受到攻击。逐渐地,攻击者和防御者之间形成了类似博弈的竞争,双方都会试图对彼此采取最佳策略,同时最大化自身的收益。为了解决该博弈,每个参与者都会基于对对手策略选择的预测,选择针对对手的最优策略。在本研究中,我们站在防御方,应用博弈论方法来防御攻击。我们使用两种随机化方法,即随机初始化和随机激活剪枝,来创建网络的多样性。此外,我们使用一种去噪技术,即超分辨率,通过在攻击前对图像进行预处理来提高模型的鲁棒性。我们的实验结果表明,这三种方法能有效提升深度学习神经网络的鲁棒性。

英文摘要:

Adversarial attacks can generate adversarial inputs by applying small but intentionally worst-case perturbations to samples from the dataset, which leads to even state-of-the-art deep neural networks outputting incorrect answers with high confidence. Hence, some adversarial defense techniques are developed to improve the security and robustness of the models and avoid them being attacked. Gradually, a game-like competition between attackers and defenders formed, in which both players would attempt to play their best strategies against each other while maximizing their own payoffs. To solve the game, each player would choose an optimal strategy against the opponent based on the prediction of the opponent's strategy choice. In this work, we are on the defensive side to apply game-theoretic approaches on defending against attacks. We use two randomization methods, random initialization and stochastic activation pruning, to create diversity of networks. Furthermore, we use one denoising technique, super resolution, to improve models' robustness by preprocessing images before attacks. Our experimental results indicate that those three methods can effectively improve the robustness of deep-learning neural networks.

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。

↑