Hierarchical Attention Neural Networks: Beyond the traditional approaches for text classification

Text classification is an important task in Natural Language Processing in which predefined categories are assigned to text documents. In this article, we’ll explore recent approaches for text classification that consider document structure as well as sentence-level attention.

In general, a text classification workflow is like this.

text classification workflow

Continue reading

Opera(Presto) Source Code leaked on DarkWeb

Leaking the source code of the proprietary tools are not a new scenario in the cyber threat arena. Recently, Windows 10 source code was leaked into “Beta Archives’ FTP”; (later removed) which is an active discussion forum on Windows Releases.

Sometimes, it may be an Insider Threat (Breach) or other times, it may be an Intrusion which ultimately classified into “Leaks”.

Continue reading

Cloud-AI – An Artificial Intelligence on the Cloud

In 2015 we started on a mission to build an Artificial Intelligence system that can interact with the web like an intelligent human being. We did a demo of our first prototype in March 2016 at NullCon conference. Today we would like to share with you few breakthroughs we have made in this research. Also, we are open-sourcing certain modules part of our use case.


CloudSek’s Cloud-AI:

Humans know how to interact with a website or mobile application based on our past learning, together with some feedback from visual aids. We identify a clickable button based on a “label” or shape or even the size and color of objects. Current computer systems do not carry their experience along with them to new tasks. This is the challenge we are solving at CloudSek. We are building  Artificial Intelligence agents that can navigate the Internet like an Intelligent human being leveraging past experiences.

Continue reading

Santa-APT: Android and Blackberry Malware Technical Analysis Part 2

CloudSek is an artificial intelligence technology-based risk management enterprise, which focuses on customized, intelligent security monitors.

Cloudsek’s SaaS-based products help a client, assess security real-time from the perspective of an attacker 24*7. Our monitors track our client’s various Internet-based resources for potential security risks. Instead of using traditional static threat detection engines and manual verification process our monitors use Machine Learning and Artificial Intelligence to identify threats.

The blog is an analysis of some critical information CloudSek acquired from our data partner.

At CloudSek we monitor and attribute all potential threats that affect Cloud services. In our previous blog we wrote about a group of attackers code named as Santa-APT that was functioning as a cyber crime unit as well as an APT. This team targeted Cloud servicing vendors as well.

Santa-APT team had multiple games and apps on Playstore as well as other android markets. These games never had all permissions required to do full data theft. The actual malware payloads came as updates.  They not only had Android Malwares but Blackberry versions too. In this blog we will provide more technical details regarding their payloads. Continue reading

Crimeware / APT Malware Masquerade as Santa Claus and Christmas Apps

addtext_com_MTcwNzQ3MTQ2NDA3

CloudSek is an artificial intelligence technology-based risk management enterprise, which focuses on customized, intelligent security monitors.

Cloudsek’s SaaS-based products help a client, assess security real-time from the perspective of an attacker 24*7. Our monitors track our client’s various Internet-based resources for potential security risks. Instead of using traditional static threat detection engines and manual verification process our monitors use Machine Learning and Artificial Intelligence to identify threats.

The blog is an analysis of some critical information CloudSek acquired from our data partner.

Overview:

CloudSek monitors were researching the activities of an APT [Advanced persistent threat ] that is targeting software companies globally.What is interesting is this APT appear to conduct widespread intellectual property theft for economic gains, targeted individuals as well as performed intelligence gathering that would be useful for governments. Based on our analysis , the attacker have recently launched campaigns to target Christmas season. Malware masquerades as Santa Claus and many similar Christmas Apps. Continue reading