|
Darkmarket Forensics
Dolejška, Daniel ; Grégr, Matěj (referee) ; Veselý, Vladimír (advisor)
Overlay networks (like Tor or I2P) create a suitable environment for criminality to thrive on the Internet. Dark marketplaces (a.k.a. cryptomarkets) are one such example of criminal activities. They act as an intermediary in the trade of illegal goods and services. This project focuses on forensic analysis of such web services and subsequent extraction of non-trivial information about the realised orders and payments from selected marketplaces. The main goal is to pinpoint the time interval when an order has been completed on selected marketplaces and its following correlation with cryptocurrency blockchains. The implemented program provides fully automated non-stop monitoring of selected cryptomarkets. That, under certain conditions, allows detection of realised purchases, detailed product and vendor monitoring and collection of various meta-data entries. Law enforcement agencies can use acquired data as support evidence regarding the operation of selected cryptomarkets and their vendors. The obtained information can also indicate current trends in products supply and demand.
|
|
An Application Utilizing esmska Plugins for Sending SMS Messages via Web Gateways
Marton, Dominik ; Očenášek, Pavel (referee) ; Rychlý, Marek (advisor)
This thesis describes the design and implementation of a console application, that utilizes esmska JavaScript modules to enable sending SMS messages from inside of user scripts via web gateways without CAPTCHA security plugin, and of a web service with REST interface making this application accessible remotely. Both are primarily made with the purpose of running on network devices with OpenWrt operating system while trying to minimise memory consumption. The whole solution is written in C with the help of libcurl library, embedded JavaScript interpreter Duktape and standard C library uClibc.
|
|
Code Detection from Control Image
Růžička, Miloslav ; Zuzaňák, Jiří (referee) ; Beran, Vítězslav (advisor)
Work deals with code detection from control image. The document presents relevant image processing techniques dealing with a noise reduction, thresholding, color models, object segmentation and OCR. This project examines advantages and disadvantages of two selected methods for object segmentation and introduces developed system for object segmentation. The developed system for object segmentation and classification is realized, evaluated and results are discussed in details.
|
|
OCR module for recognition of letters and numbers
Kapusta, Ján ; Přinosil, Jiří (referee) ; Sigmund, Milan (advisor)
This paper describes basic methods used for optical character recognition. It explains all procedures of recognition from adjustment of picture, processing, feature extracting to matching algorithms. It compares methods and algorithms for character recognition obtained graphically distorted or else modified image so-called „captcha“, used in present. Further it compares method based on invariant moments and neural network as final classifier and method based on correlation between normals and recognized characters.
|
|
Antispam protection of web pages
Orsák, David ; Míča, Ivan (referee) ; Kacálek, Jan (advisor)
This thesis deals with questions of spam especially for web pages. The work specifies the term spam, history of spam and that individual division according to way diffusion and type sight. Here is decrypted questions legislature for spam and assessment consequences for this issue. With problem of spam is closely linked the botnets, which are main sources of spam, in this thesis is decrypted how botnet work and witch botnets are the biggest in this time that mean botnet which delivered the most of spam per day. The main part this work is to defined and decrypted different ways of spam protecting websites. Here are given type of protection from basic protection for hardy form protection, name CAPTCHA. In the practical part of the thesis offers some variants CAPTCHA, which could be reused for antispam protection for web pages
|
|
CAPTCHA Recognition
Klika, Jan ; Samek, Jan (referee) ; Rozman, Jaroslav (advisor)
This thesis describes the design and implementation of an application for breaking the CAPTCHA. It also describes the history and evolution of CAPTCHA and the ways of its generating and possible techniques of its breaking. This thesis focuses on the new types of CAPTCHA, based on hard character segmentation. So the main target of this thesis is the design and implementation of the new segmentation method, allowing the recognition of modern CAPTCHAs, especially reCAPTCHA.
|
|
Automated extraction of data from HTML
Onderka, Jakub ; Koutný, Martin (referee) ; Vrba, Kamil (advisor)
This thesis deals with data extraction from web pages created in HTML language. It describes methods of downloading pages from remote server using HTTP protocol, document charset encoding and options for extraction content from elements. It also shows ways in which authors of web sites can prevent automatic web scraping. These were used to create C# applications for extraction data from two Czech Police databases – Investigation for person and Investigation for cars. These applications allow to download data from remote database, save to local database and search or show required data.
|
|
Secured access for web applications
Humpolík, Jan ; Pelka, Tomáš (referee) ; Doležel, Radek (advisor)
This thesis mainly concerns often neglected security part of each web application, but also secure access users themselves. Describes theoretically and practically modern security technology, on a web application being tested and shows a possible way of defense. Gives instructions for installing its own web server.
|
|
Semi-Supervised Approach To Train Captcha Letter Position Detetor
Bostik, Ondrej
Common Optical Character Recognition (OCR) methods benefit from the fact, that the text is distributedin images in a predictable pattern. This is not the situation with CAPTCHA systems. UtilizingOCR algorithms to overcome common web anti-abuse CAPTCHA systems is therefore a challengingtask. To train a system to overcome any CAPTCHA scheme, an attacker needs a huge dataset ofannotated images. And for some methods, the attacker needs not only the right answers but also anexact position of the character in the CAPTCHA image.Annotate the positions of the object in an image is a time-consuming task. In this paper, we proposea system, which can help to annotate the position of CAPTCHA character with minimal humaninteraction. After annotating a small sample of targeted CAPTCHA images, a YOLO-based regiondetection deep network is used to search for the characters’ locations.
|
|
Semi-Supervised Deep Learning Approach For Breaking Geocaching Captchas
Bostik, Ondrej
For nearly two decades, a substantial part of developed anti-abuse and anti-spam systems for web applications called CAPTCHA is based on imperfections in OCR (Optical Character Recognition) algorithms. But with improvements in Deep Learning in OCR, these systems are now obsolete. More and more systems can now break various text Captchas with great accuracy. Now with sufficient training dataset, almost every text-based Captcha scheme can be broken. The focus of this work is to present an idea of a semi-supervised method for reading text-based Captcha which needs only a small initial dataset. The main part of this article is dealing with the problem of training a deep learning system with only a small sample of target Captcha scheme via transfer learning.
|