Más contenido relacionado



Detecting Malicious Social Bots Based-3.pptx

  1. Detecting Malicious Social Bots Based on Click stream Sequences RAMPELLY ROSHINI (19S41A0576) MOHAMMED SUFIYAN (19S41A0559) THATIKONDA SUMANVITHA (19S41A0592) REVELLI UDAYKIRAN (19S41A0578) INTERNAL GUIDE Dr.N.Chandramouli
  2. • Social bots have been used to perform automated analytical services and provide users with improved quality of service. However, malicious social bots have also been used to disseminate false information (e.g., fake news), and this can result in real-world consequences. These features are easily imitated by social bots; thereby resulting in low accuracy of the analysis. • A novel method of detecting malicious social bots, including both features selection based on the transition probability of clickstream sequences and semi-supervised clustering, is presented in this paper Introduction:
  3. Existing system: • Malicious users in social network platforms are likely to exhibit behavior patterns that different from normal users, because their goals in maximizing their own needs and purposes (e.g., promote a certain product or certain political beliefs or ideology). • User behavior analysis is not only helpful in gaining an in-depth understanding of user intent, but it is also important to the detection of malicious social bots' accounts in online social networks.
  4. • A total of 450 thousand items of data were collected from July 1 to September 30, 2022.These data were clickstream data of normal users and social bots on CyVOD. • It includes user information viewing, video broadcasting, comment related behaviors, friend related behaviors, comment releasing in circles, and other related behaviors. Proposed System:
  5. System Requirements Software Requirements: • Coding Language : JAVA  Application Server : Tomcat 5.0  Operating System : Windows XP  Front End : HTML, Java, Jsp  Scripts : JavaScript.  Server side Script : Java Server Pages.  Database : Mysql 5.0  Database Connectivity : JDBC. Hardware Requirements: • System : Pentium IV 2.4 GHz. • Hard Disk : 1 TB. • Ram : 2 GB.
  6. UML DIAGRAM: Fig: Use case Diagram detection of malicious bots
  7. 1. OSN Server: • In this module, the OSN Server has to login by using valid user name and password. • After login successful he can do some operations such as view all user details and authorize them, list of all friends requests and response ,View all posts like images and messages user, view all Similar group users like doctors, Engineers, Business Man, etc.,. • OSN Server can add some BOTS words to the database and view the all words added by him and based on that negative words admin can find all users behavior and also produce chart for that behavior words. MODULES • Types of modules: 1.OSN Server 2.USER
  8. 2. User: • In this module, there are n numbers of users are present. • User should register with group option before doing some operations. After registration successful he has to wait for admin to authorize him and after admin authorized user can login by using authorized user name and password. • Login successful he will do some operations like view profile details, Search friends based on keyword or friends name, view the friend requests, post message with image to all friends. Find posts of friends and comment on that posts.
  9. Fig 1: OSN Login • The OSN main page is an admin page. Admin has to login through credentials. Admin can anticioate the users activites like users posts, users comments and detects malicious bots which was posted by users.
  10. Fig 2: Registration page • In Registration page we have to enter the details to register as a user. After Giving the details user has to click register tab. Now the admin has to authorize the new user. After authorization now user is successfully registered.
  11. Fig 3: Users List • The above page can shows number of users list which was authorised by admin. The user has been specialised in their group. This page is administered by admin and can also observes users activity.
  12. Fig 4: Search Friends • This page allows users to search their friends by entering name. If user has account in it then the page will shows the users profile. If not the page will shows a message like user is not found.
  13. Fig 5: Friends page • The searched user profile has been displayed after entering the name. Now the user can send the request to his friend. After this user can see the posts of his friend and can also comment on his posts.
  14. Fig 6: Post details • The above picture describes about the user’s shared post which includes post title, post description, post speciality message, posted date .Here we can also add pictures to the shared post.
  15. Fig 7: Users bots behaviour • Users bots behaviour includes details of the specified users detected by admin. The page will have user name, comments, bad type, used bot words, total bot words found.
  16. Fig 8: List of bot words • Here we can find the list of bot words which was previously listed by the admin. Here we can find the types of bot words used by users.
  17. Fig 9: Analyzing the data of malicious bots through bar graph • The frequency of bot type words posted or used can be Analysed through the bar graphs.
  18. Advantages • Transition probability of user behavior clickstreams increases by an average of 12.8%, in comparison to the detection method based on quantitative analysis of user behavior. Disadvantages • In online social networks, social bots are social accounts controlled by automated programs that can perform corresponding operations based on a set of procedures.
  19. CONCLUSION • We proposed a novel method to accurately detect malicious social bots in online social networks. Experiments showed that transition probability between user click streams based on the social situation analytics can be used to detect malicious social bots in online social platforms accurately. In future research, additional behaviors of malicious social bots will be further considered and the proposed detection approach will be extended and optimized to identify specific intentions and purposes of a broader range of malicious social bots.
  20. 1.F. Morstatter, L. Wu, T. H. Nazer, K. M. Carley, and H. Liu, ``A new approach to bot detection: Striking the balance between precision and recall,'' in Proc. IEEE/ACM Int. Conf. Adv. Social Netw Mining,San Francisco, CA, USA, Aug. 2016, pp. 533_540. 2.C. A. De Lima Salge and N. Berente, ``Is that social bot behaving unethically?''Commun. ACM, vol. 60, no. 9, pp. 29_31, Sep. 2017. REFERENCES