On Sunday 8 March 2026 at 19:03 UTC, a login endpoint flood targeted a electronics retail customer in North America. The attack peaked at 194.8 million requests per second and lasted 189 minutes. Traffic originated from 1836 autonomous systems in 61 countries, predominantly a headless-browser farm.
| Vector | login endpoint flood |
| Peak | 194.8 million requests per second |
| Duration | 189 min |
| Time to mitigation | 0.675 s |
| Attack traffic reaching origin | 0.013% |
| Legitimate traffic challenged | 0.33% |
Timeline
The attack was preceded by an extortion email received two days earlier. Request rates on the targeted routes exceeded their hourly baseline by a factor of 767 within 29 seconds. The risk score of participating clients crossed the challenge threshold automatically and proof-of-work difficulty rose with origin load.
What the customer saw
A brief increase in p99 latency of 157 ms during the first minute, then normal service.
Recommendations
- Lower challenge thresholds on authentication endpoints during high-risk events.
- Keep origin IPs out of public DNS history.
- Add a dedicated rate limit for the targeted route.
How does the proof-of-work challenge behave on older Android devices? Any numbers below Android 10?
Interesting that most attacks are under ten minutes. Our experience is similar.
Thanks! Yes — the risk score and its components are included in every log record.
This matches what we see in iGaming around big matches.
Thanks — sharing this with our on-call team.
Our auditors asked for exactly this kind of incident evidence under DORA.
The billing model is what got our finance team on board, honestly.
The point about origin IPs leaking through certificate transparency logs is underrated.