AI in Cybersecurity & Fraud Prevention
summary
Cybersecurity stacks produce billions of records/day that get distilled by XDR, NGFW logs and SIEMs into alerts, and the national registry reports >1 billion DNS queries/day; an in‑bank ML antifraud system (built 2017) fingerprints device/browser and scores payments to approve, delay or block non‑historical or beneficiary‑changed transfers; DNS detection flags domains registered yesterday with sudden query spikes, takes screenshots and logo matches, but suspension often needs legal process so human-in-the-loop remains mandatory.
AI-written summary · about
chapters (11)
- 0:00AI in cybersecurity intro
- 4:36Data volumes and AI tools
- 7:29Daily ops with AI tools
- 13:16AI and DNS fraud detection
- 16:14Banking fraud types and detection
- 24:16AI impact on incident response
- 31:09Suspending malicious domains
- 36:38Customer experience with anti-fraud
- 40:18Regulations on AI in security
- 43:52Automation vs false positives
- 45:41Q&A
related talks
11mAI-Powered Cybersecurity in the Age of Advanced Threats
22mApplying AI for Threat Detection in the World of Cybersecurity
13mAI-Powered Payment Systems
08mAI-Powered Fraud Detection in Financial System
27m"Cybertelligence": How AI is changing the face of cybersecurity
26mAI-Powered Fraud Detection in Cloud-Native Digital Payments
42mAI Math Models Help Hunting Cybersecurity Threads
29mThresholds Are for Old Threats: Demystifying AI and Machine Learning to Enhance SOC Detection