Send message to

Do you want to send the message without a subject?
Please note that your message can be maximum 1000 characters long
Special characters '<', '>' are not allowed in subject and message
reCaptcha is invalid.
reCaptcha failed because of a problem with the server.

Your message has been sent

You can find the message in your personal profile at "My messages".

An error occured

Please try again.

Make an appointment with

So that you can make an appointment, the calendar will open in a new tab on the personal profile of your contact person.

Create an onsite appointment with

So that you can make an onsite appointment, the appointment request will open in a new tab.

Forums it-sa Expo Knowledge Forum C

Revolution in Malware Detection

INLYSE: a revolutionary way of malware detection. Combination of intelligent image recognition and self-learning neural networks.

calendar_today Wed, 26.10.2022, 16:15 - 16:30

event_available On site

Action Video

south_east

Action description

south_east

Speaker

south_east

Themes

Cloud Security Endpoint Protection Data Center Secure Homeoffice

Organizer

Event

This action is part of the event Forums it-sa Expo

Action Video

grafischer Background
close

This video is available to the it-sa 365 community. 
Please register or log in with your login data.

Action description


Over the past decade, computer vision has been triumphant in a wide variety of domains. This ranges from automatic facial recognition for unlocking smartphones to autonomous driving vehicles and the detection of diseases on X-ray images.
Researchers around the world are working on computer vision AI architectures to keep improving recognition rates. These architectures dwarf one another one by one and serve the sole purpose of recognizing even the most minimal structures on images, based on which they can be classified.
These strong architectures are fully focused on the goal of classifying pixels in images, but cannot effectively process other data structures such as speech, text, or byte information from computer files. This means that the respective AI architecture must be designed specifically for the available data and the problem to be solved, and that there is no global "research race" for the latest strongest architecture.
This also applies to the problem of malware detection. Instead of developing specific AI architectures that can potentially solve the problem, inlyse is working on answering the question whether existing state-of-the-art computer vision architectures can be used to detect malware. This can be considered analogous to human medicine. A patient visits a doctor, who takes an X-ray and tries to find unusual patterns on it that indicate a disease. This is exactly the principle that inlyse wants to use for the detection of computer viruses.
For this purpose, inlyse tries to convert files into images in such a way that the generated images a.) can actually be classified by the AI, and b.) these represent a holistic graphical projection of the input file.
To do this, several difficult hurdles had to be overcome, such as converting files of different sizes into uniformly sized images without losing important information due to too much compression, of very large files, or too much noise information due to too much tearing of small files.
... read more

Downloads

Language: German

Questions and Answers: No

Speaker

show more
close

This content or feature is available to the it-sa 365 community. 
Please register or log in with your login data.