Secret Tips to Reduce Insider Threat Risks with Behavioral AI
summary
Claims that 71% of data loss is insider-driven and that behavior is predictable lead to a concrete stack: ingest Teams, Edge/Chrome, DLP telemetry and identity/device context into a custom AI model that learns per-user baselines, scores risk, and pushes real-time policy adjustment into DLPs. Demonstrations include traced exfiltration paths (USB, email, Teams/Zoom, cloud AI accounts, obfuscated files, Git/S3), an agent/SaaS that enforces rules and reduces false positives, and a privacy-by-design approach that keeps content out of analysis.
AI-written summary · about
chapters (12)
- 0:00Insider threat risks
- 0:25Data loss employee risks
- 1:06Yan’s malicious tactics
- 4:40Advanced methods Yan uses to steal data
- 7:29Yan’s data theft techniques
- 8:10Eva’s threat detection challenges
- 9:14Predicting insider risks
- 10:39Risk profiles for prevention
- 11:21Cyber Meter AI detection
- 12:24Privacy-focused monitoring
- 13:06Compliance with behavioral AI
- 13:26Q&A
related talks
23mInsider Threat Detection & Automation by Behaviour Analytics
41mCollaboration Without Data Loss: Keep IP From Leaking to Competitors
40mA Data Protection Problem: Insider Risk
21mBusiness Defence -- Managing the Insider Threat with Security Analytics
15mPredictive Techniques to Catch Insider Threats Before they Become Criminals
24mImplementing Robust AI Security for Enterprise Innovation
44mWhat Security Teams Need to Know and Do
54mInsider Threats and New Economy Industries