Microsoft security intelligence Archives - Page 20 of 20

Deep learning rises: New methods for detecting malicious PowerShell

September 3, 2019 TH Author AI and machine learning, Cybersecurity, deep learning, Endpoint security, machine learning, Microsoft Defender ATP, Microsoft security intelligence, PowerShell, Security Intelligence, Threat protection

We adopted a deep learning technique that was initially developed for natural language processing and applied to expand Microsoft Defender ATP’s coverage of detecting malicious PowerShell scripts, which continue to be a critical attack vector.
The post Deep learning rises: New methods for detecting malicious PowerShell appeared first on Microsoft Security. READ MORE HERE…

Microsoft Secure

Gartner names Microsoft a Leader in 2019 Endpoint Protection Platforms Magic Quadrant

August 23, 2019 TH Author Cybersecurity, endpoint protection platform (EPP), gartner, Magic Quadrant (MQ), Microsoft Defender ATP, Microsoft security intelligence, Windows Security

Gartner named Microsoft a Leader in the 2019 Gartner Magic Quadrant for Endpoint Protection Platforms, positioned highest in execution.
The post Gartner names Microsoft a Leader in 2019 Endpoint Protection Platforms Magic Quadrant appeared first on Microsoft Security. READ MORE HERE…

Microsoft Secure

From unstructured data to actionable intelligence: Using machine learning for threat intelligence

August 8, 2019 TH Author AI and machine learning, Automation, Cybersecurity, Endpoint security, indicators of compromise (IoC), machine learning, Microsoft Defender Advanced Threat Protection, Microsoft security intelligence, Security Intelligence, threat intelligence, TTPs, Windows Security

Machine learning and natural language processing can automate the processing of unstructured text for insightful, actionable threat intelligence.
The post From unstructured data to actionable intelligence: Using machine learning for threat intelligence appeared first on Microsoft Security. READ MORE HERE…

Microsoft Secure

A case study in industry collaboration: Poisoned RDP vulnerability disclosure and response

August 7, 2019 TH Author CVE-2019-0887, Cybersecurity, Endpoint security, Event Tracing for Windows (ETW), Exploit, Microsoft Defender Advanced Threat Protection, Microsoft security intelligence, Remote Desktop Protocol (RDP), Security Response, Vulnerability, Windows Security

Through a cross-company, cross-continent collaboration, we discovered a vulnerability, secured customers, and developed fix, all while learning important lessons that we can share with the industry.
The post A case study in industry collaboration: Poisoned RDP vulnerability disclosure and response appeared first on Microsoft Security. READ MORE HERE…

Microsoft Secure

How Windows Defender Antivirus integrates hardware-based system integrity for informed, extensive endpoint protection

July 31, 2019 TH Author assertion engine, Cybersecurity, hardware-based isolation, kernel-mode attacks, Microsoft Defender Advanced Threat Protection, Microsoft security intelligence, next generation protection, privilege escalation, runtime attestation, Security Intelligence, Threat protection, token swap, token theft, Windows Defender Antivirus, Windows Security

The deep integration of Windows Defender Antivirus with hardware-based isolation capabilities allows the detection of artifacts of attacks that tamper with kernel-mode agents at the hypervisor level.
The post How Windows Defender Antivirus integrates hardware-based system integrity for informed, extensive endpoint protection appeared first on Microsoft Security. READ MORE HERE…

Microsoft Secure

New machine learning model sifts through the good to unearth the bad in evasive malware

July 25, 2019 TH Author AI and machine learning, antivirus, Automation, Cybersecurity, detection evasion, Endpoint security, LockerGoga, machine learning, Microsoft Defender Advanced Threat Protection, Microsoft Defender ATP, Microsoft security intelligence, monotonic models, next generation protection, Windows Defender Antivirus

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.
The post New machine learning model sifts through the good to unearth the bad in evasive malware appeared first on Microsoft Security. READ MORE HERE…