Many application systems have been created and a lot of research has been done to detect suspicious messages, chats, profiles, spam emails, malicious web content URLs , as well as phishing attacks on social media. Social approach to detect spam or malware on Facebook, Twitter, Myspace was based on the information found in social media by identifying or detecting malicious URL links, spam emails, suspicious words from images and video texts. Say no to plagiarism. Get a tailor-made essay on “Why Violent Video Games Should Not Be Banned”? Get an Original Essay There are few applications that detect suspicious words embedded in images or videos using image processing and image retrieval techniques. An earlier study monitored messages sent via social networking sites and instant messages. The designed framework that prevents, predicts and provides evidence of the profile of cyberattacks when suspicious messages are sent between users, but fails to detect suspicious messages in short form and coded words sent via IM and SNM in real time . They also fail to detect suspicious words in all kinds of long and short word forms and coded words embedded in the image content. Mohd Mahmood Ali, Khaja Moizuddin Mohd and Lakshmi Rajamani are researchers who discovered the SMD framework to detect suspicious words from messages stored in the database. after users communicated via social networks {Ali2014}. This article did not focus on code words and short chat messages. This involved preventing, predicting and providing evidence of suspicious comments, tracing the profile of an individual or group committing a crime and reporting it to the E-crime service. However, the approaches used such as data mining and ontological structure semantically divided the texts of the websites with the help of the Word Net database into different attributes of threat categories, for example: murder, kidnapping and sexuality. But the ontology has not been frequently updated with new codewords discovered using a data mining approach. Rajamani, Lakshmi Ali, Mohammed Mahmood Rasheed and Mohammed Abdul presented a system designed with text safe framework thinking that recognizes suspicious messages that incite illegal movements. criminals. One framework does not focus on securing messages using encryption approaches nor does it focus on short messages. This article gives different thoughts regarding stem calculation and priority algorithm. Murugesan, Devi, Deepthi, Lavanya and Annie Princy. They proposed an automatic monitoring system for suspicious discussions in online forums and used text analysis to detect suspicious messages in online forums. They focus on automated classification to identify the most important suspicious chats {Murugesan2016}. Thivya Shilpa. Gv proposed a framework that ensures security, predicts, detects codewords and short forms of suspicious words using association rule mining techniques and ontology concept that ensures security of Chat messages stored using encryption technique. But this article does not detect suspicious words attached to the image content. Salim Almi Omar Beqqali, a researcher discovered an automatic system for detecting suspicious profiles on social networks by identifying suspicious performances and concerns .