Malicious Url Detection Using Machine Learning

•Download as PPTX, PDF•

15 likes•7,907 views

This document discusses using machine learning to detect malicious URLs. It proposes extracting various features from URLs, including querying blacklists, domain registration information, host properties, and lexical features of the URL. These features are then used to train classifiers like logistic regression to distinguish benign from malicious URLs. The approach is shown to achieve over 86.5% accuracy in detecting malicious URLs using a diverse set of over 18,000 features, performing better than blacklists alone. Future work includes scaling the approach for deployment and incorporating webpage content analysis.

Beyond Blacklists: Malicious Url Detection Using
Machine Learning

Who am I ?
• Info security Investigator @ Cisco.
• Completed Mtech from IIT Jodhpur in 2014.
• Areas of interest include machine learning,
computer vision and A.I.
• Email : satyamiitj89@gmail.com

Malicious websites
Phishing : which one is real ??

Problem in a Nutshell
6
 URL features to identify malicious Web sites
 No context, no content
 Different classes of URLs
 Benign, spam, phishing, exploits, scams...
 For now, distinguish benign vs. malicious
facebook.com fblight.com

State of the Practice
8
 Current approaches
 Blacklists [SORBS, URIBL, SURBL, Spamhaus]
 Learning on hand-tuned features [Garera et al, 2007]
 Limitations
 Cannot predict unlisted sites
 Cannot account for new features
 Arms race: Fast feedback cycle is critical
More automated approach?

URL Classification System
9
Label Example Hypothesis

Data Sets
10
 Malicious URLs
 5,000 from PhishTank (phishing)
 15,000 from Spamscatter (spam, phishing, etc)
 Benign URLs
 15,000 from Yahoo Web directory
 15,000 from DMOZ directory
 Malicious x Benign → 4 Data Sets
 30,000 – 55,000 features per data set

Algorithms
11
 Logistic regression w/ L1-norm regularization
 Other models
 Naive Bayes
 Support vector machines (linear, RBF kernels)
 Implicit feature selection
 Easier to interpret

Features to consider?
14
1) Blacklists
2) Simple heuristics
3) Domain name registration
4) Host properties
5) Lexical

(1) Blacklist Queries
15
 List of known malicious sites
 Providers: SORBS, URIBL, SURBL,
Spamhaus
http://www.bfuduuioo1fp.mobi
In blacklist?
Yes
http://fblight.com
No
In blacklist?
http://www.bfuduuioo1fp.mobi
Blacklist queries as features
........................................
........................................

(2) Manually-Selected Features
16
 Considered by previous studies
 IP address in hostname?
 Number of dots in URL
 WHOIS (domain name) registration date
stopgap.cn registered 28
June 2009
http://72.23.5.122/www.bankofamerica.com/
http://www.bankofamerica.com.qytrpbcw.stopgap.cn/

(3) WHOIS Features
17
 Domain name registration
 Date of registration, update, expiration
 Registrant: Who registered domain?
 Registrar: Who manages registration?
http://sleazysalmon.com
http://angryalbacore.com
http://mangymackerel.com
http://yammeringyellowtail.com
Registered on
29 June 2009
By SpamMedia

(4) Host-Based Features
18
 Blacklisted? (SORBS, URIBL, SURBL, Spamhaus)
 WHOIS: registrar, registrant, dates
 IP address: Which ASes/IP prefixes?
 DNS: TTL? PTR record exists/resolves?
 Geography-related: Locale? Connection speed?
75.102.60.0/2269.63.176.0/20
facebook.com fblight.com

(5) Lexical Features
19
 Tokens in URL hostname + path
 Length of URL
 Entropy of the domain name
http://www.bfuduuioo1fp.mobi/ws/ebayisapi.dll

Which feature sets?
20
Blacklist
Manual
WHOIS
Host-based
Lexical
Full
w/o WHOIS/Blacklist
4,000
# Features
13,000
4
3
17,000
30,000
26,000

Beyond Blacklists
21
Blacklist
Full features
Yahoo-PhishTank
Higher detection rate for
given false positive rate

Limitations
22
 False positives
 Sites hosted in disreputable ISP
 Guilt by association
 False negatives
 Compromised sites
 Free hosting sites
 Hosted in reputable ISP
 Future work: Web page content

Conclusion
23
 Detect malicious URLs with high accuracy
 Only using URL
 Diverse feature set helps: 86.5% w/ 18,000+
features
 Proof concept working in lab
 Future work
 Scaling up for deployment

References
 Ma, Justin, et al. "Beyond blacklists: learning
to detect malicious web sites from suspicious
URLs." Proceedings of the 15th ACM SIGKDD
international conference on Knowledge
discovery and data mining. ACM, 2009.

What's hot

Seminar on Cyber Crime

Likan Patra

Sms spam-detection

Tanvirul Islam

This document presents research on using machine learning algorithms to detect SMS spam messages. It introduces the problem of SMS spam, describes the dataset used containing over 5,000 SMS messages, and explains the preprocessing and feature extraction steps. It then evaluates the performance of various classification algorithms - Naive Bayes, SVM, k-NN, Random Forests, and AdaBoost with Decision Trees - on the SMS spam detection task, reporting the accuracy, spam caught rate, and ham blocked rate for each. It finds that Naive Bayes and SVM performed best with over 98% accuracy.

Spoofing

Sanjeev

Web spoofing involves masquerading as another user or program to gain an illegitimate advantage. There are several types of spoofing, including IP spoofing where the sender address is falsified, and web spoofing where an adversary can observe and modify web pages sent to the victim. Defenses include ingress/egress filtering to block spoofed IP addresses, and users verifying URLs and SSL certificates when entering sensitive information online.

Final spam-e-mail-detection

Partnered Health

The document presents a presentation on spam email detection. It introduces the topic and defines spam emails. It then discusses using a naïve Bayes classifier to classify emails as spam or not spam based on feature vectors. It identifies problems caused by spam emails and the objectives of detection. It reviews literature on spam prevention. The document outlines the project scope, requirements, feasibility study, testing approach using datasets, and output. It concludes that the method can effectively classify emails but may have limitations when dealing with large volumes of emails.

Face Recognition Methods based on Convolutional Neural Networks

Elaheh Rashedi

Convolutional neural networks (CNN) have improved the state of the art in many applications, especially the face recognition area. In this work, we present a review on latest face verification techniques based on Convolutional Neural Networks. In addition, we give a comparison on these techniques regarding their architecture, depth level, number of parameters in the network, and the obtained accuracy in identification and/or verification. Furthermore, as the availability of large-scale training dataset has significantly affected the performance of CNN based recognition methods, we present a preface to the most common large-scale face datasets, and then we describe some of the successful automatic data collection procedures.

Detection of Phishing Websites

Nikhil Soni

The document presents a machine learning-based approach for detecting phishing websites. It proposes using URL obfuscation, third-party service, and hyperlink-based features to train a random forest classifier. The random forest algorithm achieved 99.31% accuracy at classifying websites as legitimate or phishing. Principal component analysis was also applied to further improve the model to 99.55% accuracy. However, the approach is limited as it cannot analyze websites using captcha verification before loading. The quality and size of the training data also impacts the model performance.

Detection of phishing websites

m srikanth

The document describes a proposed system called Link Guard for detecting phishing websites and emails. Link Guard utilizes the characteristics of hyperlinks in phishing attacks to classify links as legitimate or phishing. It works by collecting URL information, storing it in a database, analyzing the links using the Link Guard algorithm, alerting users to potential phishing links, and logging events. The algorithm aims to detect both known and unknown phishing attacks in real-time across email and notification systems.

Basics of Denial of Service Attacks

Hansa Nidushan

This document discusses denial of service (DoS) attacks, including their history and types. It explains that a DoS attack is a malicious attempt to deny service to customers of a target site or network. The first major DoS attack was the 1988 Morris Worm, which infected 10% of internet computers and cost millions to clean up. Common types of DoS attacks are penetration attacks, eavesdropping, man-in-the-middle attacks, and flooding attacks, which overwhelm a target with traffic. While nothing can entirely prevent DoS attacks, defenses include firewalls, routers, switches, bandwidth limitations, and keeping systems patched. The document concludes that future DoS attacks may aim for broad destabilization rather

Attendance system based on face recognition using python by Raihan Sikdar

raihansikdar

The document discusses face recognition technology for use in an automatic attendance system. It first defines biometrics and face recognition, explaining that face recognition identifies individuals using facial features. It then covers how face recognition systems work by detecting nodal points on faces to create unique face prints. The document proposes using such a system to take student attendance in online classes during the pandemic, noting advantages like ease of use, increased security, and cost effectiveness. It provides examples of how the system would capture images, analyze features, and recognize enrolled students to record attendance automatically.

Malware Detection using Machine Learning

Cysinfo Cyber Security Community

This document discusses using machine learning for malware detection. It begins with an introduction to machine learning and feature selection for classification problems. Popular supervised learning algorithms that can be used for malware detection are discussed, including K-Nearest Neighbors (KNN), K-Means clustering, Support Vector Machines (SVM), Decision Trees, and Random Forests. Features that could be used for malware detection, such as file size, entropy, and behavioral patterns, are also outlined. The document concludes with brief mentions of neural networks, deep learning, and Python libraries that can be used like Scikit-Learn.

Phishing attacks ppt

Aryan Ragu

This document discusses phishing, which is a form of online fraud that aims to steal users' sensitive information such as usernames, passwords, and credit card details. It does this through deceptive messages that appear to come from legitimate organizations but actually lead to fake websites or download malware. The document provides information on how phishing works, techniques used to detect and prevent it, and tips for users to avoid falling victim to phishing scams.

Face recognition ppt

Santosh Kumar

This document provides an overview of facial recognition technology. It discusses the history of facial recognition, how the technology works by detecting nodal points on faces and creating faceprints for identification. It also covers implementations, comparing images to templates to verify or identify individuals, and applications in security and surveillance. Strengths are its non-invasive nature, but it can be impacted by changes in appearance.

Digital watermarking

Ankush Kr

Digital watermarking is a technique for hiding copyright information in digital content such as images, audio and video. A digital watermark is imperceptibly embedded in the digital content and can be extracted or detected to prove ownership. There are two main types of watermarks - visible watermarks that can be seen and invisible watermarks that cannot be seen by the human eye. Watermarking techniques include spatial domain and frequency domain methods. The Fast Hadamard Transform is commonly used for digital image watermarking as it allows for faster processing times and robust watermarks. The watermarking process involves embedding, attacks on the watermarked content, and detection of the watermark.

Face recognition technology

ranjit banshpal

Face recognition technology uses machine learning algorithms to identify or verify a person's identity from digital images or video frames. The process involves detecting faces, applying preprocessing techniques like filtering and scaling, training classifiers using labeled face images, and then classifying new faces. Common machine learning algorithms used include K-nearest neighbors, naive Bayes, decision trees, and locally weighted learning. The proposed system detects faces, builds a tabular dataset from pixel values, trains classifiers, and evaluates performance on a test set. Software applies techniques like detection, alignment, normalization, and matching to encode faces for comparison. Face recognition has advantages like convenience and low cost, and applications in security, banking, and more.

Presentation-Detecting Spammers on Social Networks

Ashish Arora

This document summarizes research on detecting spammers on social networks. The researchers created fake "honeypot" profiles on Facebook, Twitter, and MySpace to collect data from spammers over 12 months. They analyzed the data to identify patterns in spam bots and campaigns. Machine learning techniques were used to develop features that detected spammers with 2-3% error rates. The techniques help social networks improve security and identify malicious users spreading spam.

CYBERBULLYING DETECTION USING MACHINE LEARNING-1 (1).pdf

KumbidiGaming

The document discusses a project that aims to detect cyberbullying using machine learning. It presents a system that trains a naive bayes classifier on a dataset of bullying and non-bullying comments to classify new comments. The system is implemented using Python with Django and SQL Server. It extracts features from comments using TF-IDF before training the naive bayes model. The trained model can then detect abusive comments on social media platforms.

Unit 2

Jigarthacker

PPT on Phishing

Pankaj Yadav

This document discusses phishing, which is an attempt to acquire personal information like usernames, passwords, and credit card details under false pretenses. It covers common phishing techniques like link manipulation and website forgery. It also discusses types of phishing like deceptive, malware-based, and DNS-based phishing. The document outlines causes of phishing like misleading emails and lack of user awareness. It proposes both technical and social approaches to anti-phishing and examines the effects of phishing like identity theft and financial loss. Finally, it recommends defenses like education and detection tools to counter phishing attacks.

Phishing technology

harpinderkaur123

This document discusses the history and techniques of phishing attacks. It notes that phishing originated in the 1990s as a way to steal AOL account passwords but has since evolved to target banks, PayPal, and other financial institutions to steal credit card numbers and bank account credentials. Modern phishing uses official-looking websites, email messages, links, and social engineering to trick users into providing sensitive information. The document recommends ways for individuals and businesses to protect themselves, including being wary of unsolicited messages requesting personal details, verifying website URLs, keeping software updated, and reporting suspicious activity.

Cyber attack

Manjushree Mashal

What's hot (20)

Seminar on Cyber Crime

Sms spam-detection

Spoofing

Final spam-e-mail-detection

Face Recognition Methods based on Convolutional Neural Networks

Detection of Phishing Websites

Detection of phishing websites

Basics of Denial of Service Attacks

Attendance system based on face recognition using python by Raihan Sikdar

Malware Detection using Machine Learning

Phishing attacks ppt

Face recognition ppt

Digital watermarking

Face recognition technology

Presentation-Detecting Spammers on Social Networks

CYBERBULLYING DETECTION USING MACHINE LEARNING-1 (1).pdf

Unit 2

PPT on Phishing

Phishing technology

Cyber attack

Similar to Malicious Url Detection Using Machine Learning

Understanding Web Bots and How They Hurt Your Business

Imperva Incapsula

Orion Cassetto presented on understanding web bots and how they can hurt businesses. Bots make up over 60% of web traffic and can be used for hacking through denial of service attacks, content scraping, spam, and fraud. While some bots like search engines are legitimate, others are malicious. Cassetto suggested using bot detection and mitigation solutions to identify and block bad bots while maintaining access for good bots in order to protect websites from these threats.

Hitbkl 2012

F _

This document discusses detecting malicious network infrastructure through analyzing DNS traffic patterns. Specific techniques discussed include analyzing DNS query patterns for domain generation algorithm (DGA) domains to identify botnets. The document outlines a system built to perform passive DNS analysis to cluster similarly behaving domains and map command and control (C&C) infrastructure through techniques like WHOIS lookups and identifying domains with shared IP addresses or autonomous system numbers. Examples are provided of analyzing DNS query data step-by-step to identify known botnets like Carberp and Palevo. Automated detection and mapping of C&C infrastructure is discussed as well as potential uses of the collected data like generating blacklists or taking over botnets.

Case Study on Property Portal Data Security

Property Portal Watch

This document discusses how advanced persistent bots pose a threat to real estate portals by scraping listing data and spamming contact forms. Traditional homegrown solutions are ineffective against sophisticated bots. Lamudi, a global property portal, was experiencing performance issues and data scraping due to bot traffic 15x higher than human traffic. Lamudi implemented Distil's bot detection and mitigation solution, which uses techniques like device fingerprinting and browser validation to accurately identify and block bots without impacting users. This resulted in the elimination of data scraping, reduced form spam, improved performance, and saved engineering resources.

Ensuring Property Portal Listing Data Security

Distil Networks

Securing your property portal listing data is harder than ever. Why? Web scraping is cheap and easy. Bots simply steal whatever content they’ve been programmed to fetch – listing text, photos, and other data that should only be available to paid subscribers and legitimate consumers. Review this presentation to learn how to avoid expensive litigation by protecting your content before the theft occurs. Review the latest research on how non-human traffic has evolved over the past few years and best practices to protect both copyrighted and non-copyrightable content. Hear the results from research conducted with property portal executives on the current state of anti-scraping efforts.

How to clean up travel website traffic from bots and spammers?

tnooz

Did you know 30% of travel industry website visitors are unsavory competitors, hackers, spammers, and fraudsters? When aggressive scrapers took his website offline, Rob Gennaro, Digital Marketing Officer at Red Label Vacations, said enough was enough. The fact is, travel suppliers, OTAs, and meta search sites are all being scraped by bots which hurts their marketing metrics, SEO, website performance, and customer loyalty. You can protect your site from web-scraping competitors and fraudsters. Attend this FREE 30-minute TLearn webinar to understand: The prevalence and impact of bots on your website How to identify and block fraudsters and scrapers When a web scraper is actually good The future of online travel and website security Our panelists are: Rob Gennaro, digital marketing officer, Red Label Vacations Rami Essaid, co-founder and CEO, Distil Networks Kevin May, moderator and editor, Tnooz Nick Vivion, producer and reporter, Tnooz

Cleaning up website traffic from bots & spammers

Distil Networks

This document summarizes a webinar about how bots and web scraping impact travel websites and how companies can defend against these threats. The webinar discusses how up to 38% of traffic on travel sites are bad bots, how they scrape pricing and other data to undermine sites, and how this wasted resources and lowers revenues. It profiles Red Label Vacations' experience with bot traffic issues and how implementing Distil Networks' bot detection solution improved their performance, reduced costs, and provided visibility into bot traffic. The webinar advocates for a purpose-built bot detection solution over alternatives like CDNs or WAFs in order to accurately identify and block 99.9% of malicious bots without impacting users.

Rtp rsp16-distil networks-final-deck

G3 Communications

Are Bot Operators Eating Your Lunch?

Distil Networks

Did you know 30% of Ecommerce website visitors are unsavory competitors, hackers, and fraudsters? Fact is, online retailers are particularly susceptible to the effects of advanced bot threats, including competitive tactics like price scraping, product matching, variation tracking and availability targeting. Even worse, security breaches such as transaction fraud and account takeovers endanger the overall security of your website, customer base, and brand. When aggressive scrapers caused repeated site slowdowns, Brian Gress, Director of IT Systems & Governance at Hayneedle, said enough was enough. Key takeaways include how to: - Stop competitors from scraping your prices and monitoring your inventory - Reduce chargeback fees due to transaction fraud, carding and account hijacking - Optimize your conversion funnel and enjoy clean analytics and KPIs - Protect your brand image, reputation and SEO rankings

IRJET - An Automated System for Detection of Social Engineering Phishing Atta...

IRJET Journal

1) The document presents a machine learning approach to detect phishing URLs using logistic regression. It trains a logistic regression model on a dataset of 420,467 URLs that have been classified as either phishing or legitimate. 2) It preprocesses the URLs using tokenization before training the logistic regression model. The trained model is able to classify new URLs with 96% accuracy as either phishing or legitimate based on the URL features. 3) The proposed approach provides an automated way to detect phishing URLs in real-time and help prevent phishing attacks. Future work could involve developing a browser extension using this approach and increasing the dataset size for higher accuracy.

PUMMP: PHISHING URL DETECTION USING MACHINE LEARNING WITH MONOMORPHIC AND POL...

IJCNCJournal

Phishing scams are increasing drastically, which affects Internet users in compromising personal credentials. This paper proposes a novel feature utilization method for phishing URL detection called the Polymorphic property of features. In the initial stage, the URL-related features (46 features) were extracted. Later, a subset of features (19 out of 46) with the polymorphic property of features was identified, and they were extracted from different parts of the URL (the domain and path). After extracting the features, various machine learning classification algorithms were applied to build the machine learning model using monomorphic treatment of features, polymorphic treatment of features, and both monomorphic and polymorphic treatment of features. By the polymorphic property of features, we mean that the same feature provides different interpretations when considered in different parts of the URL. The machine learning models were built on two different datasets. A comparison of the machine learning models derived from the two datasets reveals the fact that the model built with both monomorphic and polymorphic treatment of features yielded higher accuracy in Phishing URL detection than the existing works.

PUMMP: Phishing URL Detection using Machine Learning with Monomorphic and Pol...

IJCNCJournal

IRJET - Detection and Prevention of Phishing Websites using Machine Learning ...

IRJET Journal

This document discusses approaches for detecting phishing websites using machine learning. It describes three main approaches: 1) analyzing features of the URL, 2) checking the legitimacy of the website by examining the hosting and management details, and 3) using visual appearance analysis to check the genuineness of the website. It then proposes a hybrid approach that uses blacklist/whitelist screening, heuristic analysis of website features, and visual similarity comparisons to flag potential phishing sites.

IRJET- Detecting Malicious URLS using Machine Learning Techniques: A Comp...

IRJET Journal

This document provides a literature review of different machine learning techniques for detecting malicious URLs. It first discusses traditional methods like blacklisting and heuristic approaches, noting their limitations in detecting newly generated malicious URLs. It then focuses on machine learning techniques, which involve feature extraction and representation phases to accurately detect malicious URLs while providing false positive rates. The document reviews various machine learning algorithms used for URL detection and discusses the advantages of machine learning over other techniques, as well as challenges it faces. Overall, the document analyzes the state of the art in using machine learning for malicious URL detection.

Malware detection-using-machine-learning

Security Bootcamp

This document discusses using machine learning and deep learning for malware detection. It notes that over 350,000 new malware are created daily, posing a significant threat. Traditional signature-based detection has limitations in detecting new malware. The document reviews research applying machine learning and deep learning techniques to malware detection using static and dynamic analysis of features. It then describes the authors' approach of using opcode frequency models with random forest and neural networks to classify files, achieving 97-98% precision and recall on a test set. The conclusion is that machine learning and deep learning can help address limitations of traditional approaches by enabling detection of new malware.

IRJET- Phishing Website Detection System

IRJET Journal

This document presents a proposed system for detecting phishing websites using a Chrome extension. The system compares URLs to entries in two databases - the Phishtank database of known phishing sites, and a local IndexedDB of frequently visited sites. If a match is found in either database, the Chrome extension will flag the site as potentially malicious by changing color. The system was tested on 53 URLs, achieving an accuracy of 92.45% at detecting phishing sites. The proposed system aims to alert users to phishing sites and protect them from disclosing sensitive information to attackers.

DETECTION OF PHISHING WEBSITES USING MACHINE LEARNING

IRJET Journal

The document describes research on detecting phishing websites using machine learning techniques. It provides background on phishing and how machine learning can be used to identify fraudulent websites. The researchers evaluated several algorithms (AdaBoost Classifier, XGBoost Classifier, Random Forest Classifier, Gradient Boosting Classifier, and Support Vector Machine) on a dataset of website attributes. Their results found that the Random Forest Classifier achieved the highest accuracy in determining whether a website was legitimate or a phishing site. The document discusses each algorithm and provides examples of the system's user interface and outputs classifying URLs. It concludes the Random Forest Classifier is effective for this phishing detection task and outlines opportunities for future work improving and expanding the approach.

State of the Art Analysis Approach for Identification of the Malignant URLs

IOSRjournaljce

Malicious URLs have been universally used to ascend various cyber attacks including spamming, phishing and malware. Malware, short term for malicious software, is software which is developed to penetrate computers in a network without the user’s permission or notification. Existing methods typically detect malicious URLs of a single attack type. Hence such detection systems are failed to protect the users from various attacks. Malware spreading widely throughout the area of network as consequence of this it becomes predicament in distributed computer and network systems. Malicious links are the place of origin of all attacks which circulated all over the web. Hence malicious URLs should be detected for the prevention of users from these malware attacks. In this paper we described a novel approach which analyze all types of attacks by identifying malicious URLs and secure the web users from them. This technique prevents the users from malignant URLs before visiting them. Therefore efficiency of web security gets maintained. For such anatomization we developed an analyzer which identifies URLs and examine as malicious or benign. We also developed five processes which crawl for suspicious URLs. This approach will prevent the users from all types of attacks and increase efficiency of web crawling phase.

17 00 distil rami

Property Portal Watch

This document discusses the risks of web scraping for real estate property portals. It notes that web scraping, while sometimes legitimate, can also be used maliciously to steal intellectual property and gain competitive advantages. The real estate industry saw a 300% increase in bad bot traffic in 2015. Web scrapers can replicate real estate portal data and platforms for a low cost, hurting the revenues and SEO rankings of legitimate portals. The document promotes the services of Distil Networks, which provides bot detection and blocking solutions to enhance data and clean up traffic from malicious bots.

Scraping in 60 minutes (CIJ Summer School 2019)

Paul Bradshaw

Wsdm yu

Anarkii

The document describes SBotMiner, a system for identifying bot-generated search traffic from query logs at scale. SBotMiner focuses on detecting stealthy, low-rate bots that are difficult to identify individually. It does this by leveraging the observation that bot queries are often coordinated and share common patterns when viewed in aggregate. SBotMiner groups queries that share identical queries and clicks, and analyzes properties of these groups to distinguish bots from normal users. When applied to a large query log dataset, SBotMiner identified over 123 million bot-related pageviews, accounting for 3.8% of total traffic.

Similar to Malicious Url Detection Using Machine Learning (20)

Understanding Web Bots and How They Hurt Your Business

Hitbkl 2012

Case Study on Property Portal Data Security

Ensuring Property Portal Listing Data Security

How to clean up travel website traffic from bots and spammers?

Cleaning up website traffic from bots & spammers

Rtp rsp16-distil networks-final-deck

Are Bot Operators Eating Your Lunch?

IRJET - An Automated System for Detection of Social Engineering Phishing Atta...

PUMMP: PHISHING URL DETECTION USING MACHINE LEARNING WITH MONOMORPHIC AND POL...

PUMMP: Phishing URL Detection using Machine Learning with Monomorphic and Pol...

IRJET - Detection and Prevention of Phishing Websites using Machine Learning ...

IRJET- Detecting Malicious URLS using Machine Learning Techniques: A Comp...

Malware detection-using-machine-learning

IRJET- Phishing Website Detection System

DETECTION OF PHISHING WEBSITES USING MACHINE LEARNING

State of the Art Analysis Approach for Identification of the Malignant URLs

17 00 distil rami

Scraping in 60 minutes (CIJ Summer School 2019)

Wsdm yu

More from securityxploded

Fingerprinting healthcare institutions

Malicious Url Detection Using Machine Learning

More Related Content

What's hot

What's hot (20)

Similar to Malicious Url Detection Using Machine Learning

Similar to Malicious Url Detection Using Machine Learning (20)

More from securityxploded

More from securityxploded (20)

Recently uploaded

Recently uploaded (20)

Malicious Url Detection Using Machine Learning