The sixth sense for cyber defense: Multimodal AI
Sophos X-Ops’ research, presented at Virus Bulletin 2024, uses ‘multimodal’ AI to classify spam, phishing, and unsafe web content
Similar Posts
Google Rolls Out On-Device AI Protections to Detect Scams in Chrome and Android
Bys sGoogle on Thursday announced it’s rolling out new artificial intelligence (AI)-powered countermeasures to combat scams across Chrome, Search, and Android. The tech giant said it will begin using Gemini Nano, its on-device large language model (LLM), to improve Safe Browsing in Chrome 137 on desktops. “The on-device approach provides instant insight on risky websites and…
CISA Flags Three Linux Kernel Vulnerabilities Exploited in the Wild
Bys sThe U.S. Cybersecurity and Infrastructure Security Agency (CISA) on Friday added three security flaws impacting the Linux kernel to its Known Exploited Vulnerabilities (KEV) catalog, citing evidence of active exploitation. The vulnerabilities are listed below – CVE-2025-39682 (CVSS score: 9.8) – An improper check for unusual or exceptional conditions vulnerability in the TLS receive path
Agentic AI in the SOC – Dawn of Autonomous Alert Triage
Bys sSecurity Operations Centers (SOCs) today face unprecedented alert volumes and increasingly sophisticated threats. Triaging and investigating these alerts are costly, cumbersome, and increases analyst fatigue, burnout, and attrition. While artificial intelligence has emerged as a go-to solution, the term “AI” often blurs crucial distinctions. Not all AI is built equal, especially in the SOC. Many
Kentwood, Michigan, schools say student malware disrupted Wi-Fi
Bys sDysruptionHub reports: Kentwood Public Schools said districtwide Wi-Fi was disrupted after a student used malicious software designed to interfere with the school system’s network. The district said outside experts helped isolate the issue, which affected Wi-Fi connectivity across its schools, and that the problems “appear” to have been resolved. Kentwood Public Schools serves students in……
North Korean IT Worker Fraud Linked to 2016 Crowdfunding Scam and Fake Domains
Bys sCybersecurity researchers have identified infrastructure links between the North Korean threat actors behind the fraudulent IT worker schemes and a 2016 crowdfunding scam. The new evidence suggests that Pyongyang-based threamoret groups may have pulled off illicit money-making scams that predate the use of IT workers, SecureWorks Counter Threat Unit (CTU) said in a report shared…
Cisco Patches Zero-Day RCE Exploited by China-Linked APT in Secure Email Gateways
Bys sCisco on Thursday released security updates for a maximum-severity security flaw impacting Cisco AsyncOS Software for Cisco Secure Email Gateway and Cisco Secure Email and Web Manager, nearly a month after the company disclosed that it had been exploited as a zero-day by a China-nexus advanced persistent threat (APT) actor codenamed UAT-9686. The vulnerability, tracked…