Security Research

Recently, OpenAI announced APIs for engineers to integrate ChatGPT and Whisper models into their apps and products. For some time, engineers could use the REST API calls for older models and otherwise use the ChatGPT interface through their website.

Using process creation as a case study, this research will outline the evasion-detection arms race to date, describe the weaknesses in some current detection approaches and then follow the quest for a generic approach to LRPC-based evasion.

Learn more about discovering threats by hunting through DLL load events, one way to reveal the presence of known and unknown malware in noisy process event data.

Elastic Security Labs discusses the NETWIRE trojan and is releasing a tool to dynamically extract configuration files.

Let's discuss three benefits that Hardware Stack Protections brings beyond the intended exploit mitigation capability, and explain some limitations.

In this blog, we will demonstrate how to detect each of four classes of process trampolining and release an updated PowerShell detection script – Get-InjectedThreadEx

Elastic Security Labs discusses the EMOTET trojan and is releasing a tool to dynamically extract configuration files using code emulators.

This is the first in a series focused on the Time Travel Debugging (TTD) technology developed by Microsoft that was explored in detail during a recent independent research period.

In this blog, we will briefly talk about how we fine-tuned a transformer model meant for a masked language modeling (MLM) task, to make it suitable for a classification task.