Cyber Security vs. Statistics
summary
Automates hourly parsing of Twitter hashtags (uses Python, regex) to extract IOCs, checks them against VirusTotal and a Cisco threat‑intel API (CTIA) and local monitoring, and only creates an incident when a sighting with a target appears; incidents post to Casebook and notify via WebEx. Demonstrates that with a 1% false‑positive rate and rare events alerts overwhelm teams (research cited: ~45% alerts false positives and 75% orgs waste equal time), so use intelligence‑driven hunting plus Bayesian enrichment to reduce noise.
AI-written summary · about
chapters (7)
- 0:00Welcome
- 4:59Threat hunting vs incident response
- 17:08Automation and stats in security ops
- 25:44False positives impact
- 29:12Automating threat hunting with Twitter
- 48:08Automating phishing response
- 52:47Key takeaways
related talks
30mTrawling for IOCs: Catching C2 in a Sea of Data
25mAutomating Cyber Threat Intelligence: A Practical Approach to Managing Emerging Vulnerabilities
17mIncident Response @ Scale-Building a Next Generation SOC
27mStandard Classification: Connecting the Dots: How Threat Intelligence Protect...
31mFiltering the Noise: Crafting an Actionable Threat Feed from Community-Shared Intelligence
43mCyber Threat Intelligence (Experts recommendations to enhance your security posture)
36mUsing data-driven metrics to anticipate and prevent security incidents
53mAI-equipped Threat Actors Versus AI-enhanced Cyber Tools: Who Wins?