Industry Newsllmai securitydistillation attacks
Irregular Raises $80 Million To Harden AI
6.0
Israeli AI security lab Irregular has secured a recent $80 million funding round and rising annual revenues, founders Dan Lahav and Omer Nevo say. The Tel Aviv startup, which counts clients including ChatGPT, Gemini and Claude, analyzes LLM behavior to uncover vulnerabilities such as distillation attacks before attackers exploit them, advising major firms and governments on preemptive defenses.
Key Points
- 1Raises $80 million and secures clients ChatGPT, Gemini, and Claude for AI security work
- 2Addresses vulnerabilities in LLM behavior including distillation attacks and manipulative response patterns
- 3Enables practitioners and leaders to preempt exploits and develop defense doctrines for deployments
Scoring Rationale
Notable LLM security relevance with new funding and clients, but mainly company-reported claims lacking technical peer review.
Sources
Public references used for this report.
Practice with real Logistics & Shipping data
90 SQL & Python problems · 15 industry datasets
Used by DS/ML engineers at top companies
High-Value Overnight OrdersEasyDelivered International ShipmentsMediumOn-Time Delivery Rate by CarrierHard
250 free problems · No credit card
See all Logistics & Shipping problems
