Tag: Recent News

As organizations pursue digital transformation by connecting vital equipment or creating new connected products, IoT deployments will get bigger and more common. In fact, IDC forecasts that IoT will continue to grow at double digit rates until IoT spending surpasses $1 trillion in 2022. As these IoT deployments come online, newly connected devices will expand the attack surface available to attackers, creating opportunities to target the valuable data generated by IoT.

Organizations understand the risks and are rightly worried about IoT. Bain’s research shows that security concerns are the top reason organizations have slowed or paused IoT rollouts*. Because IoT requires integrating many different technologies (heterogenous devices must be linked to IoT cloud services that connect to analytics services and business applications), organizations face the challenge of securing both the pieces of their IoT solution and the connections between those pieces. Attackers target weak spots; even one weak device configuration, cloud service, or admin account can provide a way into your solution. Your organization must monitor for threats and misconfigurations across all parts of your IoT solution: devices, cloud services, the supporting infrastructure, and the admin accounts who access them.

To give your organization IoT threat protection and security posture management across your entire IoT solution, we’re announcing the general availability of Azure Security Center for IoT. Azure Security Center allows you to protect your end-to-end IoT deployment by identifying and responding to emerging threats, as well as finding issues in your configurations before attackers can use them to compromise your deployment. As organizations use Azure Security Center for IoT to manage their security roadblocks, they remove the barriers keeping them from business transformation:

“With Azure Security Center for IoT, we can both address very real IoT threat models with the velocity of Azure and gain management control over the fastest scaling part of our business, which allows me to focus on delivering outcomes rather than hot fixing devices.” – Alex Kreilein, CISO RapidDeploy

Building secure IoT solutions with Azure Security Center

Securing IoT is challenging for many reasons: IoT deployments are complicated, creating opportunity for integration errors that attackers can exploit; IoT devices are heterogenous and often lack proper security measures; organizations may not have the skillsets or SecOps headcount to take on a new IoT security workload; and IoT deployments are difficult to monitor using traditional IT security tools. When organizations choose Microsoft for their IoT deployments, however, they get secure-by-design devices and services such as Azure Sphere and IoT Hub, end-to-end integration and monitoring from device to cloud, and the expertise from Microsoft and our partners to build a secure solution that meets their exact use case.

Azure Security Center for IoT builds on Microsoft’s secure-by-design IoT services with threat protection and security posture management designed for securing entire IoT deployments, including Microsoft and 3rd party devices. Azure Security Center is the first IoT security service from a major cloud provider that enables organizations to prevent, detect, and help remediate potential attacks on all the different components that make up an IoT deployment: from small sensors, to edge computing devices and gateways, to Azure IoT Hub, and on to the compute, storage, databases, and AI/ML workloads that organizations connect to their IoT deployments. This end-to-end protection is vital to secure IoT deployments. Although devices may be a common target for attackers, the services that store your data and the admins who manage your IoT solution are also valuable targets.

As IoT threats evolve due to creative attackers analyzing the new devices, use cases, and applications the industry creates, Microsoft’s unique threat intelligence, sourced from the more than 6 trillion signals that Microsoft collects every day, keeps your organization ahead of attackers. Azure Security Center creates a list of potential threats, ranked by importance, so security pros and IoT admins can remediate problems across devices, IoT services, connected Azure services, and the admins who use them.

Azure Security Center also creates ranked lists of possible misconfigurations and insecure settings, allowing IoT admins and security pros to fix the most important issues in their IoT security posture first. To create these security posture suggestions, Azure Security Center draws from Microsoft’s unique threat intelligence, as well as the industry standards. Customers can also port their data into SIEMs such as Azure Sentinel, allowing security pros to combine IoT security data with data from across the organization for artificial intelligence or advanced analysis.

Organizations can monitor their entire IoT solution, stay ahead of evolving threats, and fix configuration issues before they become threats. When combined with Microsoft’s secure-by-design devices, services, and the expertise we share with you and your partners, Azure Security Center for IoT provides an important way to reduce the risk of IoT while achieving your business goals. 

Next steps

*Used with permission from Bain & Company

We continuously harden machine learning protections against evasion and adversarial attacks. One of the latest innovations in our protection technology is the addition of a class of hardened malware detection machine learning models called monotonic models to Microsoft Defender ATP‘s Antivirus.

Historically, detection evasion has followed a common pattern: attackers would build new versions of their malware and test them offline against antivirus solutions. They’d keep making adjustments until the malware can evade antivirus products. Attackers then carry out their campaign knowing that the malware won’t initially be blocked by AV solutions, which are then forced to catch up by adding detections for the malware. In the cybercriminal underground, antivirus evasion services are available to make this process easier for attackers.

Microsoft Defender ATP’s Antivirus has significantly advanced in becoming resistant to attacker tactics like this. A sizeable portion of the protection we deliver are powered by machine learning models hosted in the cloud. The cloud protection service breaks attackers’ ability to test and adapt to our defenses in an offline environment, because attackers must either forgo testing, or test against our defenses in the cloud, where we can observe them and react even before they begin.

Hardening our defenses against adversarial attacks doesn’t end there. In this blog we’ll discuss a new class of cloud-based ML models that further harden our protections against detection evasion.

Most machine learning models are trained on a mix of malicious and clean features. Attackers routinely try to throw these models off balance by stuffing clean features into malware.

Monotonic models are resistant against adversarial attacks because they are trained differently: they only look for malicious features. The magic is this: Attackers can’t evade a monotonic model by adding clean features. To evade a monotonic model, an attacker would have to remove malicious features.

Monotonic models explained

Last summer, researchers from UC Berkeley (Incer, Inigo, et al, “Adversarially robust malware detection using monotonic classification”, Proceedings of the Fourth ACM International Workshop on Security and Privacy Analytics, ACM, 2018) proposed applying a technique of adding monotonic constraints to malware detection machine learning models to make models robust against adversaries. Simply put, the said technique only allows the machine learning model to leverage malicious features when considering a file – it’s not allowed to use any clean features.

Figure 1. Features used by a baseline versus a monotonic constrained logistic regression classifier. The monotonic classifier does not use cleanly-weighted features so that it’s more robust to adversaries.

Inspired by the academic research, we deployed our first monotonic logistic regression models to Microsoft Defender ATP cloud protection service in late 2018. Since then, they’ve played an important part in protecting against attacks.

Figure 2 below illustrates the production performance of the monotonic classifiers versus the baseline unconstrained model. Monotonic-constrained models expectedly have lower outcome in detecting malware overall compared to classic models. However, they can detect malware attacks that otherwise would have been missed because of clean features.

Figure 2. Malware detection machine learning classifiers comparing the unconstrained baseline classifier versus the monotonic constrained classifier in customer protection.

The monotonic classifiers don’t replace baseline classifiers; they run in addition to the baseline and add additional protection. We combine all our classifiers using stacked classifier ensembles–monotonic classifiers add significant value because of the unique classification they provide.

How Microsoft Defender ATP uses monotonic models to stop adversarial attacks

One common way for attackers to add clean features to malware is to digitally code-sign malware with trusted certificates. Malware families like ShadowHammer, Kovter, and Balamid are known to abuse certificates to evade detection. In many of these cases, the attackers impersonate legitimate registered businesses to defraud certificate authorities into issuing them trusted code-signing certificates.

LockerGoga, a strain of ransomware that’s known for being used in targeted attacks, is another example of malware that uses digital certificates. LockerGoga emerged in early 2019 and has been used by attackers in high-profile campaigns that targeted organizations in the industrial sector. Once attackers are able breach a target network, they use LockerGoga to encrypt enterprise data en masse and demand ransom.

Figure 3. LockerGoga variant digitally code-signed with a trusted CA

When Microsoft Defender ATP encounters a new threat like LockerGoga, the client sends a featurized description of the file to the cloud protection service for real-time classification. An array of machine learning classifiers processes the features describing the content, including whether attackers had digitally code-signed the malware with a trusted code-signing certificate that chains to a trusted CA. By ignoring certificates and other clean features, monotonic models in Microsoft Defender ATP can correctly identify attacks that otherwise would have slipped through defenses.

Very recently, researchers demonstrated an adversarial attack that appends a large volume of clean strings from a computer game executable to several well-known malware and credential dumping tools – essentially adding clean features to the malicious files – to evade detection. The researchers showed how this technique can successfully impact machine learning prediction scores so that the malware files are not classified as malware. The monotonic model hardening that we’ve deployed in Microsoft Defender ATP is key to preventing this type of attack, because, for a monotonic classifier, adding features to a file can only increase the malicious score.

Given how they significantly harden defenses, monotonic models are now standard components of machine learning protections in Microsoft Defender ATP‘s Antivirus. One of our monotonic models uniquely blocks malware on an average of 200,000 distinct devices every month. We now have three different monotonic classifiers deployed, protecting against different attack scenarios.

Monotonic models are just the latest enhancements to Microsoft Defender ATP’s Antivirus. We continue to evolve machine learning-based protections to be more resilient to adversarial attacks. More effective protections against malware and other threats on endpoints increases defense across the entire Microsoft Threat Protection. By unifying and enabling signal-sharing across Microsoft’s security services, Microsoft Threat Protection secures identities, endpoints, email and data, apps, and infrastructure.

Geoff McDonald (@glmcdona),Microsoft Defender ATP Research team
with Taylor Spangler, Windows Data Science team

---

Talk to us

Questions, concerns, or insights on this story? Join discussions at the Microsoft Defender ATP community.

Follow us on Twitter @MsftSecIntel.