Goto

Collaborating Authors

Computer vision and deep learning provide new ways to detect cyber threats

#artificialintelligence

The Transform Technology Summits start October 13th with Low-Code/No Code: Enabling Enterprise Agility. The last decade's growing interest in deep learning was triggered by the proven capacity of neural networks in computer vision tasks. If you train a neural network with enough labeled photos of cats and dogs, it will be able to find recurring patterns in each category and classify unseen images with decent accuracy. What else can you do with an image classifier? In 2019, a group of cybersecurity researchers wondered if they could treat security threat detection as an image classification problem.


Computer vision can help spot cyber threats with startling accuracy

#artificialintelligence

This article is part of our reviews of AI research papers, a series of posts that explore the latest findings in artificial intelligence. The last decade's growing interest in deep learning was triggered by the proven capacity of neural networks in computer vision tasks. If you train a neural network with enough labeled photos of cats and dogs, it will be able to find recurring patterns in each category and classify unseen images with decent accuracy. What else can you do with an image classifier? In 2019, a group of cybersecurity researchers wondered if they could treat security threat detection as an image classification problem.


ObliqueRAT Trojan now lurks in images on compromised websites

ZDNet

Cyberattackers behind ObliqueRAT campaigns are now disguising the Trojan in benign image files on hijacked websites. The ObliqueRAT Remote Access Trojan (RAT), discovered in early 2020, has been traced back to attacks against organizations in South Asia. When first discovered, the malware was described as a "simple" RAT with the typical, core functionality of a Trojan focused on data theft -- such as the ability to exfiltrate files, connect to a command-and-control (C2) server, and the ability to terminate existing processes. The malware is also able to check for any clues indicating its target is sandboxed, a common practice for cybersecurity engineers to implement in reverse-engineering malware samples. Since its initial discovery, ObliqueRAT has been upgraded with new technical capabilities and utilizes a wider set of initial infection vectors.


Don't get fooled by this malware-ridden MSI Afterburner fake

PCWorld

PC enthusiasts adore MSI's Afterburner utility, and it's easy to see why. The free GPU monitoring tool can be used for everything from overclocking to checking your graphics card's temperature to capturing gameplay footage, and better yet, it works with both Nvidia GeForce and AMD Radeon hardware--a versatile feature set unmatched by most rivals. But now bad actors are piggybacking on Afterburner's popularity to potentially trick people into downloading malware, MSI warns. "MSI is informing the public of a malicious software being disguised as the official MSI Afterburner software. The malicious software is being unlawfully hosted on a suspicious website impersonating as MSI's official website with the domain name https://afterburner-msi.space.


Using Machine Learning to Detect Malicious URLs

#artificialintelligence

With the growth of Machine Learning in the past few years, many tasks are being done with the help of machine learning algorithms. Unfortunately or fortunately, there has been little work done on security with machine learning algorithms. So I thought of presenting some at Fsecurify. A few days ago, I had this idea about what if we could detect a malicious URL from a non-malicious URL using some machine learning algorithm. There has been some research done on the topic so I thought that I should give it a go and implement something from scratch.