On Wednesday 14 April 2021 at 13:10 UTC, a HTTP GET flood targeted a healthcare portal customer in the Middle East. The attack peaked at 99.6 million requests per second and lasted 88 minutes. Traffic originated from 4094 autonomous systems in 48 countries, predominantly residential proxy networks.
| Vector | HTTP GET flood |
| Peak | 99.6 million requests per second |
| Duration | 88 min |
| Time to mitigation | 0.416 s |
| Attack traffic reaching origin | 0.048% |
| Legitimate traffic challenged | 0.76% |
Timeline
The attack was preceded by no stated motive. Request rates on the targeted routes exceeded their hourly baseline by a factor of 425 within 35 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
Checkout conversion was unchanged compared with the same hour of the previous week.
Recommendations
- Enable log streaming to your SIEM for faster correlation.
- Keep origin IPs out of public DNS history.
- Review allow-listed partner ranges quarterly.
Thanks — sharing this with our on-call team.
Any plans to support per-tenant limits keyed on a JWT claim?
Could you share the dataset behind the percentages?
Thanks! Yes — the risk score and its components are included in every log record.
We moved from a scrubbing provider to always-on last year; time to mitigation went from minutes to basically nothing.