Author Archives: chadskipper
Author Archives: chadskipper
The current reality has pushed users, applications, and data to the edge of the network —where traditional perimeter security solutions have historically fallen short. Threat actors know this, of course, and have spent the past nine months targeting the weakest link in the security stack: the user.
Email and web browsing continue to be popular attack vectors. Security vendors have beefed up web and email security, but issues with legacy architectures are letting some attacks slip through. Information and context derived from advanced threat intelligence remain the most powerful weapons in a security team’s arsenal. Advanced technologies such as artificial intelligence and machine learning can help scan, detect, and warn at scale, but they’re not bulletproof. Increasingly sophisticated threat actors, powered by AI and ML, are finding ways to evade threat detection.
Security professionals interested in learning more about the current state of advanced threat inspection, threat intelligence, and the emerging technologies that power these capabilities should check out the following sessions:
Artificial intelligence and machine learning are powerful, indeed essential, components of security Continue reading
The security community has found an important application for machine learning (ML) in its ongoing fight against cybercriminals. Many of us are turning to ML-powered security solutions like NSX Network Detection and Response that analyze network traffic for anomalous and suspicious activity. In turn, these ML solutions defend us from threats better than other solutions can by drawing on their evolving knowledge of what a network attack looks like.
Attackers are well-aware of the fact that security solutions are using AI and ML for security purposes. They also know that there are certain limitations when it comes to applying artificial intelligence to computer security. This explains why cyber criminals are leveraging ML to their advantage in something known as adversarial machine learning.
In this post I’ll explain just what adversarial machine learning is and what it is not. To start, the label itself can be a bit misleading. It sounds like criminals are actually using ML as part of their attack. But that is not the case. The simple explanation is that they’re using more conventional methods to understand how security solutions are using ML so that they can then figure out how to Continue reading
Detecting Malware Without Feature Engineering Using Deep Learning
Nowadays, machine learning is routinely used in the detection of network attacks and the identification of malicious programs. In most ML-based approaches, each analysis sample (such as an executable program, an office document, or a network request) is analyzed and a number of features are extracted. For example, in the case of a binary program, one might extract the names of the library functions being invoked, the length of the sections of the executable, and so forth.
Then, a machine learning algorithm is given as input a set of known benign and known malicious samples (called the ground truth). The algorithm creates a model that, based on the values of the features contained in the samples, is the ground truth dataset, and the model is then able to classify known samples correctly. If the dataset from which the algorithm has learned is representative of the real-world domain, and if the features are relevant for discriminating between benign and malicious programs, chances are that the learned model will generalize and allow for the detection of previously unseen malicious samples.
The Role of Feature Engineering
Even though the description Continue reading
Everywhere I look, someone’s talking about machine learning (ML) or artificial intelligence (AI). These two technologies are shaping important conversations in multiple sectors, especially marketing and sales, and are at risk of becoming overused and misunderstood buzzwords, if they haven’t already. The technologies have also drawn the attention of security professionals over the past few years, with some believing that AI is ready to transform information security.
Despite this hype, there’s still a lot of confusion around AI and ML and their utility for information security. In this blog post, I would like to correct some misperceptions. Let’s start by differentiating machine learning from artificial intelligence in general.
Machine Learning vs. Artificial Intelligence: Understanding the Difference
Artificial intelligence is the science of trying to replicate intelligent, human-like behavior. There are multiple ways of achieving this — machine learning is one of them. For example, a type of AI system that does not involve machine learning is an expert system, in which the skills and decision process of an expert are captured through a series of rules and heuristics.
Machine Learning is a specific type of AI. An ML system analyzes a large data set in Continue reading
In any given attack campaign, bad actors have a specific goal in mind. This goal may involve accessing a developer’s machine and stealing a project’s source code, sifting through a particular executive’s emails, or exfiltrating customer data from a server that’s responsible for hosting payment card information. All they need to do is compromise the system that has what they want. It’s just that easy.
Or is it?
In reality, it’s a little more complicated than that. When attackers compromise an asset in a network, that device usually is not their ultimate destination. To accomplish their goal, bad actors are likely to break into a low-level web server, email account, employee endpoint device, or some other starting location. They’ll then move laterally from this initial compromise through the network to reach their intended target. The initial compromise seldom causes severe damage. Thinking about this another way: if security teams can detect the lateral movement before the attackers reach their intended targets, they can prevent the attacker from successfully completing the mission.
But what exactly is lateral movement, and how does it work? In this blog, we’ll look at some of the most common types of lateral movement and Continue reading
Back in 2018, some cybersecurity vendors were reporting that cryptomining malware had infected organizations roughly 10 times more than ransomware. But since then, ransomware has climbed back to the top of the cybercrime landscape. Europol named ransomware as the top cyber threat organizations faced in 2019. And its impact is increasing:
“Even though law enforcement has witnessed a decline in the overall volume of ransomware attacks, those that do take place are more targeted, more profitable and cause greater economic damage. As long as ransomware provides relatively easy income for cybercriminals and continues to cause significant damage and financial losses, it is likely to remain the top cybercrime threat.”
Putting the Dominance of Ransomware into Perspective
Targeted attacks aren’t the only factor behind the ongoing prevalence of ransomware. Several other forces are also at play. Here are just a few of them.
The Rising Costs of Ransomware Infections
Higher ransomware amounts are common. A 2020 report indicated the average cost to recover from a ransomware attack more than doubled from $41,198 to a staggering $84,116. The Wall Street Journal reported that claims managers at Continue reading
Hiding malware in encrypted traffic is a tactic increasingly employed by bad actors to conceal attacks. By one estimate, 60% of cyberattacks carried out in 2019 would leverage encryption, and that was predicted to increase another 10% in 2020. Having an understanding of how your security solutions can recognize or prevent threats within SSL traffic is therefore extremely important, particularly since many such tools don’t provide that ability. In this blog, we’ll outline the ways in which security solutions can work with encrypted network traffic.
The Security Challenges Surrounding Encrypted Network Traffic
We all understand one of the goals of encrypting network traffic: to protect the confidentiality and privacy of sensitive data in motion. However, encryption also poses a challenge to most network security products —if these products cannot inspect the payload of connections, they lose their ability to detect and respond to threats.
The Rise of Encrypted Data
The use of encryption on the Internet has risen dramatically, which on the whole is a good thing. For example, the Google Transparency Report shows that the percentage of encrypted web traffic on the Internet has steadily increased, from around 50% in 2014 to Continue reading