On Sunday 12 September 2021 at 07:58 UTC, a HTTP/2 rapid reset targeted a fashion retail customer in Latin America. The attack peaked at 723.8 million requests per second and lasted 146 minutes. Traffic originated from 1761 autonomous systems in 70 countries, predominantly misconfigured open reflectors.
| Vector | HTTP/2 rapid reset |
| Peak | 723.8 million requests per second |
| Duration | 146 min |
| Time to mitigation | 0.829 s |
| Attack traffic reaching origin | 0.076% |
| Legitimate traffic challenged | 0.48% |
Timeline
The attack was preceded by a breaking political story. Request rates on the targeted routes exceeded their hourly baseline by a factor of 333 within 24 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
The customer’s status page stayed green throughout; they learned about the attack from our notification.
Recommendations
- Keep origin IPs out of public DNS history.
- Review allow-listed partner ranges quarterly.
- Lower challenge thresholds on authentication endpoints during high-risk events.
Nice to read a vendor blog that admits what went wrong.
Solid runbook advice. The DNS-at-2am point hit home.
Thanks — sharing this with our on-call team.
Our auditors asked for exactly this kind of incident evidence under DORA.
Could you share the dataset behind the percentages?
Clear and practical, thanks.
Would love a follow-up on how you handle HTTP/3 fingerprinting.