Filters








1,418 Hits in 5.4 sec

Special Issue on Advances in Deep Learning

Diego Gragnaniello, Andrea Bottino, Sandro Cumani, Wonjoon Kim
2020 Applied Sciences  
Nowadays, deep learning is the fastest growing research field in machine learning and has a tremendous impact on a plethora of daily life applications, ranging from security and surveillance to autonomous  ...  driving, automatic indexing and retrieval of media content, text analysis, speech recognition, automatic translation, and many others.[...]  ...  Acknowledgments: This special issue would not be possible without the contributions of various talented authors, professional and hardworking reviewers, and committed editorial team of Applied Sciences  ... 
doi:10.3390/app10093172 fatcat:kdowatxbprdhbkmox62nlqyquq

Adversarial Security Attacks and Perturbations on Machine Learning and Deep Learning Methods [article]

Arif Siddiqi
2019 arXiv   pre-print
The adversaries can exploit the training and testing data of the learning models or can explore the workings of those models for launching advanced future attacks.  ...  The ever-growing big data and emerging artificial intelligence (AI) demand the use of machine learning (ML) and deep learning (DL) methods.  ...  Machine learning (also known as shallow learning) and deep learning with their learning methods that consists of algorithms and models and the use and input of different data types and sizes allow to handle  ... 
arXiv:1907.07291v1 fatcat:7an2zwnhmveqncl3cpopgcousy

Deep Learning in the Biomedical Applications: Recent and Future Status

Ryad Zemouri, Noureddine Zerhouni, Daniel Racoceanu
2019 Applied Sciences  
Deep neural networks represent, nowadays, the most effective machine learning technology in biomedical domain.  ...  This paper reviews the major deep learning concepts pertinent to such biomedical applications. Concise overviews are provided for the Omics and the BBMI.  ...  The resulting model is less general than a Boltzmann machine, but is still useful, for example it can learn to extract interesting features from images.  ... 
doi:10.3390/app9081526 fatcat:srjvngtufbhstfcvn4mvhmrdve

A Robust Approach for Securing Audio Classification Against Adversarial Attacks [article]

Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich
2019 arXiv   pre-print
This poses a security concern about the safety of machine learning models since the adversarial attacks can fool such models toward the wrong predictions.  ...  In this paper we first review some strong adversarial attacks that may affect both audio signals and their 2D representations and evaluate the resiliency of the most common machine learning model, namely  ...  FGSM, BIM, etc.) are quite applicable for 2D audio representations. This is a critical issue and poses a security concern for machine learning models for audio, either shallow (e.g.  ... 
arXiv:1904.10990v2 fatcat:6sjrddcyynentpgdfpu3as74o4

FineFool: Fine Object Contour Attack via Attention [article]

Jinyin Chen, Haibin Zheng, Hui Xiong, Mengmeng Su
2018 arXiv   pre-print
Machine learning models have been shown vulnerable to adversarial attacks launched by adversarial examples which are carefully crafted by attacker to defeat classifiers.  ...  Deep learning models cannot escape the attack either.  ...  deep model for adversarial examples generated by attack methods.  ... 
arXiv:1812.01713v1 fatcat:4yzxvlw3njeslhe3lbfvvpl7ay

SSIMLayer: Towards Robust Deep Representation Learning via Nonlinear Structural Similarity [article]

Ahmed Abobakr, Mohammed Hossny, Saeid Nahavandi
2018 arXiv   pre-print
more robustness against noise perturbations and adversarial attacks.  ...  However, increasing network depth imposes difficulties on training and increases model complexity.  ...  Acknowledgements This research was fully supported by the Institute for Intelligent Systems Research and Innovation (IISRI) at Deakin University, Australia.  ... 
arXiv:1806.09152v2 fatcat:lkg3o2uitjfrzb4uc7bh5chuxe

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey [article]

Naveed Akhtar, Ajmal Mian
2018 arXiv   pre-print
Deep learning is at the heart of the current rise of machine learning and artificial intelligence.  ...  For images, such perturbations are often too small to be perceptible, yet they completely fool the deep learning models.  ...  Space of adversarial examples Tabacof and Eduardo [25] generated adversarial examples for shallow and deep network classifiers on MNIST [10] and ImageNet [11] datasets and probed the pixel space  ... 
arXiv:1801.00553v3 fatcat:xfk7togp5bhxvbxtwox3sckqq4

Adversarial Machine Learning in Image Classification: A Survey Towards the Defender's Perspective [article]

Gabriel Resende Machado, Eugênio Silva, Ronaldo Ribeiro Goldschmidt
2020 arXiv   pre-print
Here, novel taxonomies for categorizing adversarial attacks and defenses are introduced and discussions about the existence of adversarial examples are provided.  ...  Deep Learning algorithms have achieved the state-of-the-art performance for Image Classification and have been used even in security-critical applications, such as biometric recognition systems and self-driving  ...  of adversarial examples; • The discussion of promising research paths for future works on Adversarial Machine Learning.  ... 
arXiv:2009.03728v1 fatcat:ysprss2tebcwrh4agv73v2mbpy

RAILS: A Robust Adversarial Immune-inspired Learning System [article]

Ren Wang, Tianqi Chen, Stephen Lindsly, Cooper Stansbury, Alnawaz Rehemtulla, Indika Rajapakse, Alfred Hero
2022 arXiv   pre-print
The benefits of RAILS are empirically demonstrated under eight types of adversarial attacks on a DNN adversarial image classifier for several benchmark datasets, including: MNIST; SVHN; CIFAR-10; and CIFAR  ...  RAILS' evolutionary optimization process explicitly captures the tradeoff between robustness (diversity) and accuracy (specificity) of the network, and represents a new immune-inspired perspective on adversarial  ...  International Conference on Machine Learning, 2019. [30] Zhong-Qiu Zhao, Peng Zheng, Shou-tao Xu, and Xindong Wu. Object detection with deep learning: A review.  ... 
arXiv:2107.02840v2 fatcat:xtgroy5pczgfvcpuvskgooinke

Generative Art Inspired by Nature, Using NodeBox [chapter]

Tom De Smedt, Ludivine Lechat, Walter Daelemans
2011 Lecture Notes in Computer Science  
We demonstrate how it can be used for evolutionary computation in the context of computer games and art, and discuss some of our recent research with the aim to simulate (artistic) brainstorming using  ...  NodeBox is a free application for producing generative art. This paper gives an overview of the nature-inspired functionality in NodeBox and the artworks we created using it.  ...  (shallow parsing), using machine learning and statistical methods trained on large annotated corpora.  ... 
doi:10.1007/978-3-642-20520-0_27 fatcat:f7lkzyofdrggbncumfmliolx4q

Vision at A Glance: Interplay between Fine and Coarse Information Processing Pathways [article]

Zilong Ji, Xiaolong Zou, Tiejun Huang, Si Wu
2020 arXiv   pre-print
Our model consists of two convolution neural networks: one mimics the P-pathway, referred to as FineNet, which is deep, has small-size kernels, and receives detailed visual inputs; the other mimics the  ...  Object recognition is often viewed as a feedforward, bottom-up process in machine learning, but in real neural systems, object recognition is a complicated process which involves the interplay between  ...  Secondly, a large volume of comparative studies has shown that human vision is much more robust to noise than machine learning models, with the classical example of adversarial noise [30] .  ... 
arXiv:2009.05101v1 fatcat:epgmhjrjtnhflgqrydu655aa54

Adversarial Attacks against Face Recognition: A Comprehensive Study

Fatemeh Vakhshiteh, Ahmad Nickabadi, Raghavendra Ramachandra
2021 IEEE Access  
The advent of deep learning methods resolved the limitations of traditional methods.  ...  Recent studies show that (deep) FR systems exhibit an intriguing vulnerability to imperceptible or perceptible but natural-looking adversarial input images that drive the model to incorrect output predictions  ...  The face representation for recognition has taken sequential forms of holistic learning, local feature learning, shallow learning, and deep learning [30] .  ... 
doi:10.1109/access.2021.3092646 fatcat:7cj5z57wxvcbvjmckifkobraoq

Deep Learning for Procedural Content Generation

Jialin Liu, Sam Sndograss, Ahmed Khalifa, Sebastian Risi, Georgios N. Yannakakis, Julian Togelius
2020 Zenodo  
purposes but are rarely used today, and envisages some limitations and potential future directions of deep learning for procedural content generation.  ...  This article surveys the various deep learning methods that have been applied to generate game content directly or indirectly, discusses deep learning methods that could be used for content generation  ...  Adversarial Learning Adversarial learning (AL) models are perfect for generating content represented by pixel-based images or 2D array of tiles, such as levels as a map, landscapes and sprites.  ... 
doi:10.5281/zenodo.4415242 fatcat:6q4swrsefvhhde2v6mepsoagg4

RAILS: A Robust Adversarial Immune-inspired Learning System

Ren Wang, Tianqi Chen, Stephen Lindsly, Cooper Stansbury, Alnawaz Rehemtulla, Indika Rajapakse, Alfred Hero
2022 IEEE Access  
Codes for the results in this paper are available at https://github.com/wangren09/RAILS. INDEX TERMS Bio-inspired deep learning, adversarial robustness, deep network defense strategies.  ...  The benefits of RAILS are empirically demonstrated under eight types of adversarial attacks on a DNN adversarial image classifier for several benchmark datasets, including: MNIST; SVHN; CIFAR-10; and CIFAR  ...  [15] , [16] ; and (4) deep adversarial learning architectures [17] , [18] .  ... 
doi:10.1109/access.2022.3153036 fatcat:74mjn2m5hzgj7oljfsrbhaeooy

Adversarial Machine Learning Attacks and Defense Methods in the Cyber Security Domain [article]

Ihai Rosenberg and Asaf Shabtai and Yuval Elovici and Lior Rokach
2021 arXiv   pre-print
In recent years machine learning algorithms, and more specifically deep learning algorithms, have been widely used in many fields, including cyber security.  ...  However, machine learning systems are vulnerable to adversarial attacks, and this limits the application of machine learning, especially in non-stationary, adversarial environments, such as the cyber security  ...  The machine learning techniques (and thus the attacks on them) can be divided into two groups: traditional (or shallow) machine learning and deep learning techniques.Table 1summarizes the attacks in the  ... 
arXiv:2007.02407v3 fatcat:rj3qomvg4bfb5p3atsct4winji
« Previous Showing results 1 — 15 out of 1,418 results