Baseten breaks down its security threat model as agent swarms accelerate attacks
baseten · x · 2026-11-21
Baseten published the first post in a security blog series: agent swarms now scan for weak points around the clock and can go from first foothold to exfiltrated data in minutes. The company runs 100+ clusters across 20+ clouds, each held to the same security standard before serving traffic. The post walks through its threat model, controls, and a checklist for auditing your own fleet or evaluating providers, with upcoming posts on API key hygiene, container/network security, and detection & response.
More from Infra
- Nvidia's rivals are vying to be the 'Central Bank' of AI, says investor — GavinSBaker · 2026-11-21
- Benchmarking 11 open models' post-GQA attention: up to 139x less memory at 128K — bariskasikci · 2026-11-21
- Anthropic files for Nasdaq IPO — why you should keep a local open-source LLM as backup — alex_verem · 2026-11-21
- Microsoft launches MAI Licensed Weights; Purdue researcher asks to run them on own hardware — marlene_zw · 2026-11-21
- Looped CED cuts KV-cache memory 36.8x on 552B model, but encoder loops cost compute — teortaxesTex · 2026-11-21
- Agents are sessions, not requests: Google explains sizing GKE node pools for agent workloads — rseroter · 2026-11-21