paper-with-me

홈 › Papers

Decision Boundary Analysis of Adversarial Examples

2018-01-01 · ICLR 2018 1 · Warren He, Bo Li, Dawn Song

Deep neural networks (DNNs) are vulnerable to adversarial examples, which are carefully crafted instances aiming to cause prediction errors for DNNs. Recent research on adversarial examples has examined local neighborhoods in the input space of DNN models. However, previous work has limited what regions to consider, focusing either on low-dimensional subspaces or small balls. In this paper, we argue that information from larger neighborhoods, such as from more directions and from greater distances, will better characterize the relationship between adversarial examples and the DNN models. First, we introduce an attack, OPTMARGIN, which generates adversarial examples robust to small perturbations. These examples successfully evade a defense that only considers a small ball around an input instance. Second, we analyze a larger neighborhood around input instances by looking at properties of surrounding decision boundaries, namely the distances to the boundaries and the adjacent classes. We find that the boundaries around these adversarial examples do not resemble the boundaries around benign examples. Finally, we show that, under scrutiny of the surrounding decision boundaries, our OPTMARGIN examples do not convincingly mimic benign examples. Although our experiments are limited to a few specific attacks, we hope these findings will motivate new, more evasive attacks and ultimately, effective defenses.

📄 PDF Abstract BibTeX

Code (1)

sunblaze-ucb/decision-boundaries 공식 구현 tf

Similar Papers 제목 키워드 기반

LADDER: Latent Boundary-guided Adversarial Training

2022-06-08 · Xiaowei Zhou, Ivor W. Tsang, Jie Yin

Deep Neural Networks (DNNs) have recently achieved great success in many classification tasks. Unfortunately, they are vulnerable to adversarial attacks that generate adversarial examples with a small perturbation to foo…

Adversarial Robustness

Towards the Desirable Decision Boundary by Moderate-Margin Adversarial Training

2022-07-16 · Xiaoyu Liang, Yaguan Qian, Jianchang Huang, Xiang Ling 외

Adversarial training, as one of the most effective defense methods against adversarial attacks, tends to learn an inclusive decision boundary to increase the robustness of deep learning models. However, due to the large …

Enhancing the Robustness of Deep Neural Networks by Boundary Conditional GAN

2019-02-28 · Ke Sun, Zhanxing Zhu, Zhouchen Lin

Deep neural networks have been widely deployed in various machine learning tasks. However, recent works have demonstrated that they are vulnerable to adversarial examples: carefully crafted small perturbations to cause m…

Data Augmentation

The Dimpled Manifold Model of Adversarial Examples in Machine Learning

2021-06-18 · Adi Shamir, Odelia Melamed, Oriel BenShmuel

The extreme fragility of deep neural networks, when presented with tiny perturbations in their inputs, was independently discovered by several research groups in 2013. However, despite enormous effort, these adversarial …

BIG-bench Machine Learning

Trojans and Adversarial Examples: A Lethal Combination

2021-01-01 · Guanxiong Liu, Issa Khalil, Abdallah Khreishah, Hai Phan

In this work, we naturally unify adversarial examples and Trojan backdoors into a new stealthy attack, that is activated only when 1) adversarial perturbation is injected into the input examples and 2) a Trojan backdoor …