Results 291 to 300 of about 5,389,393 (319)
Some of the next articles are maybe not open access.
Robust Android Malware Detection against Adversarial Example Attacks
The Web Conference, 2021Adversarial examples pose severe threats to Android malware detection because they can render the machine learning based detection systems useless. How to effectively detect Android malware under various adversarial example attacks becomes an essential ...
Heng Li +5 more
semanticscholar +1 more source
Towards Multiple Black-boxes Attack via Adversarial Example Generation Network
ACM Multimedia, 2021The current research on adversarial attacks aims at a single model while the research on attacking multiple models simultaneously is still challenging.
Mingxing Duan +4 more
semanticscholar +1 more source
SmsNet: A New Deep Convolutional Neural Network Model for Adversarial Example Detection
IEEE transactions on multimedia, 2021The emergence of adversarial examples has had a significant impact on the development and application of deep learning. In this paper, a novel convolutional neural network model, the stochastic multifilter statistical network (SmsNet), is proposed for ...
Jinwei Wang +6 more
semanticscholar +1 more source
Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing
ACM Multimedia, 2020Machine learning fairness concerns about the biases towards certain protected or sensitive group of people when addressing the target tasks. This paper studies the debiasing problem in the context of image classification tasks.
Yi Zhang, Jitao Sang
semanticscholar +1 more source
Review on Image Processing Based Adversarial Example Defenses in Computer Vision
2020 IEEE 6th Intl Conference on Big Data Security on Cloud (BigDataSecurity), IEEE Intl Conference on High Performance and Smart Computing, (HPSC) and IEEE Intl Conference on Intelligent Data and Security (IDS), 2020Recent research works showed that deep neural networks are vulnerable to adversarial examples, which are usually maliciously created by carefully adding deliberate and imperceptible perturbations to examples. Several states of the art defense methods are
Meikang Qiu, Han Qiu
semanticscholar +1 more source
Principal Component Adversarial Example
IEEE Transactions on Image Processing, 2020Despite having achieved excellent performance on various tasks, deep neural networks have been shown to be susceptible to adversarial examples, i.e., visual inputs crafted with structural imperceptible noise.
Yonggang Zhang +4 more
semanticscholar +1 more source
On The Generation of Unrestricted Adversarial Examples
2020 50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W), 2020Adversarial examples are inputs designed by an adversary with the goal of fooling the machine learning models. Most of the research about adversarial examples have focused on perturbing the natural inputs with the assumption that the true label remains unchanged.
Mehrgan Khoshpasand +1 more
openaire +1 more source
POSTER: Detecting Audio Adversarial Example through Audio Modification
Conference on Computer and Communications Security, 2019Deep neural networks (DNNs) perform well in the fields of image recognition, speech recognition, pattern analysis, and intrusion detection. However, DNNs are vulnerable to adversarial examples that add a small amount of noise to the original samples ...
Hyun Kwon, H. Yoon, Ki-Woong Park
semanticscholar +1 more source
New algorithm to generate the adversarial example of image
, 2020This paper focuses on the algorithm to generate adversarial example of image. Firstly a new memristive chaotic mapping was proposed. Then two chaotic sequences based on the constructed memristive chaotic mapping are adopted to design the algorithm to ...
Bo Wang, F. Zou, X. W. Liu
semanticscholar +1 more source
On the Salience of Adversarial Examples
2019Adversarial examples are beginning to evolve as rapidly as the deep learning models they are designed to attack. These intentionally-manipulated inputs attempt to mislead the targeted model while maintaining the appearance of innocuous input data. Countermeasures against these attacks that take a global approach tend to be lossy to the original data ...
openaire +1 more source