Comment on Transferability and Input Transformation with Additive Noise
Adversarial attacks have verified the existence of the vulnerability of neural networks. By adding small perturbations to a benign example, adversarial attacks successfully generate adversarial examples that lead misclassification of deep learning models. More importantly, an adversarial example generated from a specific model can also deceive other models without modification. We call this phenomenon ``transferability". Here, we analyze the relationship between transferability and input transformation with additive noise by mathematically proving that the modified optimization can produce more transferable adversarial examples.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Improving the Transferability of Adversarial Examples by Feature Augmentation
Despite the success of input transformation-based attacks on boosting adversarial transferability, the performance is unsatisfying due to the ignorance of the discrepancy across models. In this paper, we propose a simple…
DiversityImproving the Transferability of Adversarial Examples with Arbitrary Style Transfer
Deep neural networks are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on clean inputs. Although many attack methods can achieve high success rates in the white-box setting, the…
Domain GeneralizationStyle TransferUnsupervised Domain AdaptationEnhancing Adversarial Transferability through Block Stretch and Shrink
Adversarial attacks introduce small, deliberately crafted perturbations that mislead neural networks, and their transferability from white-box to black-box target models remains a critical research focus. Input transform…
Admix: Enhancing the Transferability of Adversarial Attacks
Deep neural networks are known to be extremely vulnerable to adversarial examples under white-box setting. Moreover, the malicious adversaries crafted on the surrogate (source) model often exhibit black-box transferabili…
Structure Invariant Transformation for better Adversarial Transferability
Given the severe vulnerability of Deep Neural Networks (DNNs) against adversarial examples, there is an urgent need for an effective adversarial attack to identify the deficiencies of DNNs in security-sensitive applicati…
Adversarial AttackDiversity