Robust Detection of Adversarial Attacks by Modeling the Intrinsic Properties of Deep Neural Networks
It has been shown that deep neural network (DNN) based classifiers are vulnerable to human-imperceptive adversarial perturbations which can cause DNN classifiers to output wrong predictions with high confidence. We propose an unsupervised learning approach to detect adversarial inputs without any knowledge of attackers. Our approach tries to capture the intrinsic properties of a DNN classifier and uses them to detect adversarial inputs. The intrinsic properties used in this study are the output distributions of the hidden neurons in a DNN classifier presented with natural images. Our approach can be easily applied to any DNN classifiers or combined with other defense strategy to improve robustness. Experimental results show that our approach demonstrates state-of-the-art robustness in defending black-box and gray-box attacks.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Are L2 adversarial examples intrinsically different?
Deep Neural Network (DDN) has achieved notable success in various tasks, including many security concerning scenarios. However, a considerable amount of work has proved its vulnerability to adversaries. We unravel the pr…
Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
Deep Neural Networks (DNNs) have recently been shown to be vulnerable against adversarial examples, which are carefully crafted instances that can mislead DNNs to make errors during prediction. To better understand such …
Adversarial DefenseGradID: Adversarial Detection via Intrinsic Dimensionality of Gradients
Despite their remarkable performance, deep neural networks exhibit a critical vulnerability: small, often imperceptible, adversarial perturbations can lead to drastically altered model predictions. Given the stringent re…
Autonomous DrivingMedical DiagnosisUnity is strength: Improving the Detection of Adversarial Examples with Ensemble Approaches
A key challenge in computer vision and deep learning is the definition of robust strategies for the detection of adversarial examples. Here, we propose the adoption of ensemble approaches to leverage the effectiveness of…
UnityAttackDist: Characterizing Zero-day Adversarial Samples by Counter Attack
Deep Neural Networks (DNNs) have been shown vulnerable to adversarial attacks, which could produce adversarial samples that easily fool the state-of-the-art DNNs. The harmfulness of adversarial attacks calls for the defe…