paper-with-me

홈 › Papers

Improving Transformation-based Defenses against Adversarial Examples with First-order Perturbations

2021-03-08 · Haimin Zhang, Min Xu

Deep neural networks have been successfully applied in various machine learning tasks. However, studies show that neural networks are susceptible to adversarial attacks. This exposes a potential threat to neural network-based intelligent systems. We observe that the probability of the correct result outputted by the neural network increases by applying small first-order perturbations generated for non-predicted class labels to adversarial examples. Based on this observation, we propose a method for counteracting adversarial perturbations to improve adversarial robustness. In the proposed method, we randomly select a number of class labels and generate small first-order perturbations for these selected labels. The generated perturbations are added together and then clamped onto a specified space. The obtained perturbation is finally added to the adversarial example to counteract the adversarial perturbation contained in the example. The proposed method is applied at inference time and does not require retraining or finetuning the model. We experimentally validate the proposed method on CIFAR-10 and CIFAR-100. The results demonstrate that our method effectively improves the defense performance of several transformation-based defense methods, especially against strong adversarial examples generated using more iterations.

📄 PDF Abstract BibTeX arXiv:2103.04565

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

Error Diffusion Halftoning Against Adversarial Examples

2021-01-23 · Shao-Yuan Lo, Vishal M. Patel

Adversarial examples contain carefully crafted perturbations that can fool deep neural networks (DNNs) into making wrong predictions. Enhancing the adversarial robustness of DNNs has gained considerable interest in recen…

Adversarial RobustnessQuantization

SEC4SR: A Security Analysis Platform for Speaker Recognition

2021-09-04 · Guangke Chen, Zhe Zhao, Fu Song, Sen Chen 외

Adversarial attacks have been expanded to speaker recognition (SR). However, existing attacks are often assessed using different SR models, recognition tasks and datasets, and only few adversarial defenses borrowed from …

Speaker Recognition

Barrage of Random Transforms for Adversarially Robust Defense

2019-06-01 · CVPR 2019 6 · Edward Raff, Jared Sylvester, Steven Forsyth, Mark McLean

Defenses against adversarial examples, when using the ImageNet dataset, are historically easy to defeat. The common understanding is that a combination of simple image transformations and other various defenses are insuf…

On the Limitations of Stochastic Pre-processing Defenses

2022-06-19 · Yue Gao, Ilia Shumailov, Kassem Fawaz, Nicolas Papernot

Defending against adversarial examples remains an open problem. A common belief is that randomness at inference increases the cost of finding adversarial inputs. An example of such a defense is to apply a random transfor…

Adversarial Robustness

Provable Defenses against Spatially Transformed Adversarial Inputs: Impossibility and Possibility Results

2019-05-01 · ICLR 2019 5 · Xinyang Zhang, Yifan Huang, Chanh Nguyen, Shouling Ji 외

One intriguing property of neural networks is their inherent vulnerability to adversarial inputs, which are maliciously crafted samples to trigger target networks to misbehave. The state-of-the-art attacks generate adver…