Machine Learning

In our previous entry, we examined how credentials were being stored and logged in cleartext on compute instances (CIs) created in Azure Machine Learning (AML) service and the risks posed by the same. This article examines an information disclosure bug we found in one of the cloud agents used in the AML service and sheds light on the importance of threat modeling the agents’ features to uncover silent and hidden attack surfaces.

We discuss the present state of the malicious uses and abuses of AI and ML and the plausible future scenarios in which cybercriminals might abuse these technologies for ill gain.

We look into developments in end-to-end deep learning for cybersecurity and provide insights into its current and future effectiveness.

Trend Micro Cloud App Security detected and blocked 12.7 million high-risk threats that passed through the built-in security of cloud-based email services. We provide an in-depth report on the notable trends and stories from 2019 to help organizations prepare.

We listed a rundown of PoCs and real-life attacks where machine learning was weaponized to get a clearer picture of what is possible and what is already a reality with regard to machine learning-powered cyberthreats.

Multiple government procurement services were targeted by a credential harvesting campaign that uses bogus pages to steal login credentials.

We have developed a machine learning model called TrendX Hybrid Model that uses two training phases — pre-training and training — and allows us to correlate static and behavior features to improve detection rates and reduce false positives.

Almost 4,000 domains and 62 phishing kit variants used to target Microsoft users were uncovered within an observation window of 262 days, according to new report.

A new variant of HDDCryptor aka Mamba was uncovered recently. The ransomware has been known to use DiskCryptor to encrypt disk and network files and overwrite the Master Boot Record (MBR).