Filters








2,136 Hits in 3.1 sec

On robust image spam filtering via comprehensive visual modeling

Jialie Shen, Robert H. Deng, Zhiyong Cheng, Liqiang Nie, Shuicheng Yan
2015 Pattern Recognition  
In addition, a resampling based learning framework is developed to effectively integrate random forest and linear discriminative analysis (LDA) to generate comprehensive signature of spam images.  ...  In this paper, we report a novel system called RoBoTs (Robust BoosTrap based spam detector) to support accurate and robust image spam filtering.  ...  Image classification based approach The image classification for spam detection is to train a classifier on the feature vector representations of a set of spam and legitimate images.  ... 
doi:10.1016/j.patcog.2015.02.027 fatcat:7bxwrdqm4zggncvpn3dj7ifdwi

A hybrid spam detection method based on unstructured datasets

Yeqin Shao, Marcello Trovati, Quan Shi, Olga Angelopoulou, Eleana Asimakopoulou, Nik Bessis
2015 Soft Computing - A Fusion of Foundations, Methodologies and Applications  
In particular, the former is based on sparse representation based classification, which focuses on the global and local image features, and a dictionary learning technique to achieve a spam and a ham subdictionary  ...  In particular, the former is based on sparse representation based classification, which focuses on the global and local image features, and a dictionary learning technique to achieve a spam and a ham sub-dictionary  ...  The key of image spam detection and classification lies in the discriminative features and the distinguishable classifier.  ... 
doi:10.1007/s00500-015-1959-z fatcat:mdmauifbjvb5zjhaxdlrgt7rqi

ReP-ETD: A Repetitive Preprocessing technique for Embedded Text Detection from images in spam emails

Asha S Manek, D K Shamini, Veena H Bhat, P Deepa Shenoy, M. Chandra Mohan, K R Venugopal, L M Patnaik
2014 2014 IEEE International Advance Computing Conference (IACC)  
Currently, image spam is evaluated to be roughly 50% of all spam traffic and is still on the rise, thus a serious research issue.  ...  Filtering mails is one of the popular approaches used to block spam mails.  ...  Then an ANN was trained on these images using a supervised learning approach and the model was tested for classification of new samples of spam images.  ... 
doi:10.1109/iadcc.2014.6779387 fatcat:fnkdyq6cire3dl6b75mfwrojeu

A review of machine learning approaches to Spam filtering

Thiago S. Guzella, Walmir M. Caminhas
2009 Expert systems with applications  
In this paper, we present a comprehensive review of recent developments in the application of machine learning algorithms to Spam filtering, focusing on both textual-and image-based approaches.  ...  Two particularly important aspects not widely recognized in the literature are discussed: the difficulties in updating a classifier based on the bag-of-words representation and a major difference between  ...  Acknowledgements This work was supported by grants from UOL, through its Bolsa Pesquisa program (process number 20060519110414a), FAPEMIG and CNPq.  ... 
doi:10.1016/j.eswa.2009.02.037 fatcat:gf5z34w6arcdzh2w36tgefqppa

AGCDetNet: An Attention-guided Network for Building Change Detection in High-resolution Remote Sensing Images

Kaiqiang Song, Jie Jiang
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
A spatial attention module (SPAM) promotes the discrimination between the changed objects and the background by adding the learned spatial attention to the deep features.  ...  AGCDetNet learns to enhance the feature representation of change information and achieve accuracy improvements using spatial-and channelattention.  ...  Spatial Attention Module The main concern of SPAM is to learn a spatial attention map to promote discrimination between the change objects and the background in deep features.  ... 
doi:10.1109/jstars.2021.3077545 fatcat:emqmdfxegrcd3hxpafxraw4jtu

A survey and experimental evaluation of image spam filtering techniques

Battista Biggio, Giorgio Fumera, Ignazio Pillai, Fabio Roli
2011 Pattern Recognition Letters  
In this paper we give a comprehensive survey and categorisation of computer vision and pattern recognition techniques proposed so far against image spam, and make an experimental analysis and comparison  ...  It consists in embedding the spam message into an attached image, which is often randomly modified to evade signature-based detection, and obfuscated to prevent text recognition by OCR tools.  ...  This work was partly supported by a grant from Regione Autonoma della Sardegna awarded to B. Biggio and I.  ... 
doi:10.1016/j.patrec.2011.03.022 fatcat:s6y5g4wsqjco3ab4zcbz7ud5tu

Analysis of adversarial attacks against CNN-based image forgery detectors [article]

Diego Gragnaniello, Francesco Marra, Giovanni Poggi, Luisa Verdoliva
2018 arXiv   pre-print
With the ubiquitous diffusion of social networks, images are becoming a dominant and powerful communication channel.  ...  In this paper we analyze the vulnerability of CNN-based image forensics methods to adversarial attacks, considering several detectors and several types of attack, and testing performance on a wide range  ...  23.76 https://www.kaggle.com/c/sp-society-camera-model-identification  ... 
arXiv:1808.08426v1 fatcat:fo7nn4j5ereknh46po2tfre7gu

A Machine Learning Based Email Spam Classification Framework Model: Related Challenges and Issues

2020 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
There has been a lot of effort to render spam filtering more efficient in classifying e-mails as either ham (valid messages) or spam (unwanted messages) through the ML classifiers.  ...  Spam emails, also known as non-self, are unsolicited commercial emails or fraudulent emails sent to a particular individual or company, or to a group of individuals.  ...  Furthermore, the creation and enhancement of software classifiers that can discriminate between genuine e-mail and spam presents a continuing problem.  ... 
doi:10.35940/ijitee.d1561.029420 fatcat:rvgjclq2svh6za56sm4czuwn5i

Spatial Domain-Based Nonlinear Residual Feature Extraction for Identification of Image Operations

Xiaochen Yuan, Tian Huang
2020 Applied Sciences  
Then, we propose applying a deep learning technique to the extracted SDNR features to detect and classify a variety of image operations.  ...  In this paper, a novel approach that uses a deep learning technique is proposed to detect and identify a variety of image operations.  ...  Then, similarly, we apply a deep learning method of a five-layer CNN to the extracted SDNR features to produce the detection and identification results.  ... 
doi:10.3390/app10165582 fatcat:2itecuktgvh73k7z5dfkdbqndq

Spam Fighting in Social Tagging Systems [chapter]

Sasan Yazdani, Ivan Ivanov, Morteza AnaLoui, Reza Berangi, Touradj Ebrahimi
2012 Lecture Notes in Computer Science  
Since filtering spam annotations and spammers is time-consuming if it is done manually, machine learning approaches can be employed to facilitate this process.  ...  However, noisy and spam annotations often make it difficult to perform an efficient search.  ...  Identification-based (or detection-based) approaches create a model from users' information, activities and interactions to efficiently detect and filter spam users (or content) from social tagging systems  ... 
doi:10.1007/978-3-642-35386-4_33 fatcat:bhp4vlfdwrbsxnjpnecmqxmjla

A Survey of Game Theoretic Approaches for Adversarial Machine Learning in Cybersecurity Tasks

Prithviraj Dasgupta, Joseph Collins
2019 The AI Magazine  
A critical vulnerability of these algorithms is that they are susceptible to adversarial attacks by which a malicious entity called an adversary deliberately alters the training data to misguide the learning  ...  Most of these techniques use supervised learning algorithms that rely on training the algorithm to classify incoming data into categories, using data encountered in the relevant domain.  ...  Acknowledgments The authors would like to acknowledge support from the US Office of Naval Research Summer Faculty Research program for supporting the work of Prithviraj Dasgupta at the US Naval Research  ... 
doi:10.1609/aimag.v40i2.2847 fatcat:aptetzccqfcwpcszm6s4kj7vtu

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.[...]  ...  Finally, we place on record our gratitude to the editorial team of Applied Sciences and special thanks to Daria Shi, Managing Editor, from MDPI Branch Office, Beijing.  ... 
doi:10.3390/app10093172 fatcat:kdowatxbprdhbkmox62nlqyquq

Detecting image spam using visual features and near duplicate detection

Bhaskar Mehta, Saurabh Nangia, Manish Gupta, Wolfgang Nejdl
2008 Proceeding of the 17th international conference on World Wide Web - WWW '08  
SVMs (Support Vector Machines) are used to train classifiers using judiciously decided color, texture and shape features.  ...  The second solution offers a novel approach for near duplication detection in images.  ...  learn probabilistic models of images, but a hidden assumption is that the images are similar in size.  ... 
doi:10.1145/1367497.1367565 dblp:conf/www/MehtaNGN08 fatcat:xxqyvd33wfg7nir4267s3327my

Asian Stamps Identification and Classification System [article]

Behzad Mahaseni, Nabhan D. Salih
2017 arXiv   pre-print
The goal is to classify a given stamp to a certain country and also identify the year it is published.  ...  We propose a new approach for stamp recognition based on describing a given stamp image using color information and texture information.  ...  We proposed a classification model which uses a classical machine learning approach to classify stamps to five different countries and 5 different years.  ... 
arXiv:1709.05065v1 fatcat:lr6yo5jpindybl3cd4k6w4rkae

An Exploratory Analysis on Identification of Plants Based on the Structural Features using Machine Learning

Chaithaly B B
2020 International Journal for Research in Applied Science and Engineering Technology  
The classifiers such as Random Forest Classifier, Neural Networks, Linear Regression and K-NN are used for classification and recognition.  ...  Modern technologies such as Machine learning[ML], Deep learning, Neural networks help is an automatic recognition of plants. For recognition of plants, a single set of features are inefficient.  ...  Steps of supervised machine learning Jana waldchen, Patrick mader [12] Image-based approach is considered a very good approach for plant species identification.  ... 
doi:10.22214/ijraset.2020.32708 fatcat:nnorpn3e5zda7hcafeq4u3gkgm
« Previous Showing results 1 — 15 out of 2,136 results