Vern  Greenholt

Vern Greenholt

1598071740

📱Adversarial Attacks on SMS Spam Detectors

Note:_ The methodology behind the approach discussed in this post stems from a collaborative publication between myself and Irene Anthi._

INTRODUCTION

Spam SMS text messages often show up unexpectedly on our phone screens. That’s aggravating enough, but it gets worse. Whoever is sending you a spam text message is usually trying to defraud you. Most spam text messages don’t come from another phone. They often originate from a computer and are delivered to your phone via an email address or an instant messaging account.

There exists several security mechanisms for automatically detecting whether an email or an SMS message is spam or not. These approaches often rely on machine learning. However, the introduction of such systems may also be subject to attacks.

The act of deploying attacks towards machine learning based systems is known as Adversarial Machine Learning (AML). The aim is to exploit the weaknesses of the pre-trained model which may have “blind spots” between the data points it has seen during training. More specifically, by automatically introducing slight perturbations to the unseen data points, the model may cross a decision boundary and classify the data as a different class. As a result, the model’s effectiveness can significantly be reduced.

In the context of SMS spam detection, AML can be used to manipulate textual data by including perturbations to cause spam data to be classified as being not spam, consequently bypassing the detector.

DATASET AND DATA PRE-PROCESSING

The SMS Spam Collection is a set of SMS tagged messages that have been collected for SMS spam research. It contains a set of 5,574 English SMS text messages which are tagged according to whether they are spam (425 message) or not-spam (3,375).

#editors-pick #adversarial-attack #nlp #machine-learning #data-science #deep learning

What is GEEK

Buddha Community

📱Adversarial Attacks on SMS Spam Detectors

The Ultimate Guide To SMS: Spam or Ham Detector

TL;DR Understanding spam or ham classifier from the aspect of Artificial Intelligence concepts, work with various classification algorithms, and select high accuracy producing algorithms and develop the Python Flask App.


The blog is a series of the blog post, if you haven’t read the theoretical Artificial Intelligence concept of spam or ham classifier, please take a ten-minute read at:

The Ultimate Guide To SMS: Spam or Ham Detector

Detailed Report for Developing Spam or Ham Classifier: Part 1

towardsdatascience.com

We have covered in Part 1

  • Theoretical AI Concept Regarding Spam or Ham Classifier
  • Classification Algorithms

We will cover here in Part 2

  • Exploring Data Source
  • Data Preparation
  • Exploratory Data Analysis

We will cover in next Part 3

  • NaĂŻve Bayes Behind Spam or Ham
  • Performance Measurement Criterion
  • Development of Spam or Ham Detector

Exploring Data Source

The dataset is originally sourced from Tiago A. Almeida (talmeida ufscar.br) Department of Computer Science Federal University of Sao Carlos (UFSCar) Sorocaba, Sao Paulo — Brazil and taken from UCI Machine Learning [15].

The collection is composed by just one text file, where each line has the correct class followed by the raw message.

#data-science #python #artificial-intelligence #sms #spam

Alec  Nikolaus

Alec Nikolaus

1596544440

The Ultimate Guide To SMS: Spam or Ham Detector

TL;DR Understanding spam or ham classifier from the aspect of Artificial Intelligence concepts, work with various classification algorithms, and select high accuracy producing algorithm and develop the Python Flask App for SMS: spam or ham detector.

Short Message Services (SMS) is far more than just a technology for a chat. SMS technology evolved out of the global system for mobile communications standard, an internationally accepted[1]. Spam is the abuse of electronic messaging systems to send unsolicited messages in bulk indiscriminately [2]. While the most widely recognized form of spam is email spam, the term is applied to similar abuses in other media and mediums. SMS Spam in the context is very similar to email spams, typically, unsolicited bulk messaging with some business interest. SMS spam is used for commercial advertising and spreading phishing links. Commercial spammers use malware to send SMS spam because sending SMS spam is illegal in most countries. Sending spam from a compromised machine reduces the risk to the spammer because it obscures the provenance of the spam. SMS can have a limited number of characters, which includes alphabets, numbers, and a few symbols. A look through the messages shows a clear pattern. Almost all of the spam messages ask the users to call a number, reply by SMS, or visit some URL. This pattern is observable by the results obtained by a simple SQL query on the spam corpus[3]. The low price and the high bandwidth of the SMS network have attracted a large amount of SMS spam [4].

People classify SMS Spam as annoying (32.3%), wasting time(24.8%), and violating personal privacy (21.3%)[5].

Every time SMS spam arrives at a user’s inbox, and the mobile phone alerts the user to the incoming message. When the user realizes that the message is unwanted, he or she will be disappointed, and also SMS spam takes up some of the mobile phone’s storage.

SMS spam detection is an important task where spam SMS messages are identified and filtered. As more significant numbers of SMS messages are communicated every day, it is challenging for a user to remember and correlate the newer SMS messages received in context to previously received SMS. Thus, using the knowledge of artificial intelligence with the amalgamation of machine learning, and data mining we will try to develop web-based SMS text spam or ham detector.

This is three parts of blog series, where we will understand the in and out of spam or ham classifier from the aspect of Artificial Intelligence concepts, and work with various classification algorithms in jupyter notebook and select the one algorithm based on performance criteria. Then, we will develop the Python web-based SMS text spam or ham detector.

What will we cover here

  • Theoretical AI Concept Regarding Spam or Ham Classifier
  • Classification Algorithms
  • Exploring Data Source
  • Data Preparation
  • Exploratory Data Analysis
  • NaĂŻve Bayes Behind Spam or Ham
  • Performance Measurement Criterion
  • Development of Spam or Ham Detector

#spam #sms #data-science #python #artificial-intelligence

Alec  Nikolaus

Alec Nikolaus

1596718980

The Ultimate Guide To SMS: Spam or Ham Detector

TL;DR Understanding spam or ham classifier from the aspect of Artificial Intelligence concepts, work with various classification algorithms, and select high accuracy producing algorithms and develop the Python Flask App.

The blog is a series of the blog post, if you haven’t read the theoretical Artificial Intelligence concept of spam or ham classifier and have not worked with algorithms in jupyter notebook, please explore it at:

The Ultimate Guide To SMS: Spam or Ham Detector

Detailed Report for Developing Spam or Ham Classifier: Part 1

towardsdatascience.com

The Ultimate Guide To SMS: Spam or Ham Detector

Detailed Report For Developing Spam or Ham Classifier: Part 2

towardsdatascience.com

We have covered in part 1 & 2

  • Theoretical AI Concept Regarding Spam or Ham Classifier
  • Classification Algorithms
  • Exploring Data Source
  • Data Preparation
  • Exploratory Data Analysis

We will cover here in Part 3

  • NaĂŻve Bayes Behind Spam or Ham
  • Performance Measurement Criterion
  • Development of Spam or Ham Detector

Image for post

Designed by Author. Illustration from unDraw.

NaĂŻve Bayes Behind Spam or Ham

One of the most useful applications of the Bayes rule is the so-called naive Bayes classifier.

The NaĂŻve Bayes algorithm creates a probabilistic model for classification of SMS messages. Even though all features contribute towards the overall probability of classification, NaĂŻve Bayes algorithm assumes that the features are statistically independent of each other[10]. Although this assumption may not hold true for all cases, NaĂŻve Bayes algorithm has shown promising results in comparison with other well-known classification algorithms. An advantage of NaĂŻve Bayes is that it only requires a small amount of training data to estimate the parameters necessary for classification and as small dataset size NaĂŻve Bayes classifiers can outperform the more powerful alternatives[18]. Because independent variables are assumed, only the variances of the variables for each class need to be determined and not the entire covariance matrix.

Image for post

#sms #python #spam #data-science #artificial-intelligence

Vern  Greenholt

Vern Greenholt

1598071740

📱Adversarial Attacks on SMS Spam Detectors

Note:_ The methodology behind the approach discussed in this post stems from a collaborative publication between myself and Irene Anthi._

INTRODUCTION

Spam SMS text messages often show up unexpectedly on our phone screens. That’s aggravating enough, but it gets worse. Whoever is sending you a spam text message is usually trying to defraud you. Most spam text messages don’t come from another phone. They often originate from a computer and are delivered to your phone via an email address or an instant messaging account.

There exists several security mechanisms for automatically detecting whether an email or an SMS message is spam or not. These approaches often rely on machine learning. However, the introduction of such systems may also be subject to attacks.

The act of deploying attacks towards machine learning based systems is known as Adversarial Machine Learning (AML). The aim is to exploit the weaknesses of the pre-trained model which may have “blind spots” between the data points it has seen during training. More specifically, by automatically introducing slight perturbations to the unseen data points, the model may cross a decision boundary and classify the data as a different class. As a result, the model’s effectiveness can significantly be reduced.

In the context of SMS spam detection, AML can be used to manipulate textual data by including perturbations to cause spam data to be classified as being not spam, consequently bypassing the detector.

DATASET AND DATA PRE-PROCESSING

The SMS Spam Collection is a set of SMS tagged messages that have been collected for SMS spam research. It contains a set of 5,574 English SMS text messages which are tagged according to whether they are spam (425 message) or not-spam (3,375).

#editors-pick #adversarial-attack #nlp #machine-learning #data-science #deep learning

I am Developer

1613800156

Laravel 8 Send SMS to Mobile with Nexmo Tutorial

Laravel 8 send sms using nexmo example. In this tutorial, you will learn how to integrate sms gateway and send sms notification to mobile using nexmo in laravel 8 app.

This tutorial will guide you step by step on how to send send sms to mobile with nexmo in laravel 8 app. Now, You need to follow the some step to done laravel nexmo message.

First of all, visit the following link https://dashboard.nexmo.com/sign-in and create nexmo account. Get client id and secret from nexom account.

https://www.tutsmake.com/laravel-8-send-sms-to-mobile-with-nexmo-example/

#send sms with nexmo on laravel #nexmo message send sms #laravel send sms notification #nexmo sms installation laravel #how to integrate sms gateway in laravel