ai-security
Network Traffic Hashing
Hashing network traffic creates a tamper-evident record of what data has transited a link. We benchmark line-rate hashing at 400GbE across CPU and DPU hardware, with an interactive dashboard of the results.
Notes
Short technical notes from Amodo engineers — research, methods, and works in progress.
2026
ai-security
Memory Wipes - Performance Analysis
Wiping cluster memory and proving that it's been wiped. Initial experiments with H200s.
ai-security
An Inference Verification Prototype — Stage 1
Our first attempt at AI inference verification: implementing and testing DiFR on a tray of H100s against example model attacks (append and append-on-trigger), across 37,500 prompt runs.
ai-security
Example Schemes for Verifying High-Stakes AI Agreements
Recomputation-based schemes for verifying that an AI cluster ran the workloads it declared — covering inference (TOPLOC, Token-DiFR) and pre-training — plus the non-determinism, game theory, and practicalities that make them work.
ai-security
(Deprecated) Memory Wiping - A First Test
Wiping cluster memory and proving that it's been wiped. Initial experiments with H200s.
ai-security
A Few Reasons to Develop AI Verification Technology
Verification technologies might be useful even if you're not shooting for an international agreement. Here are a few reasons why.
ai-security
Verification Is a Ladder
Verification is a process, not a one-shot solution. A ladder of technical mechanisms can build trust towards high-stakes coordination over AI — and nuclear verification history shows how the early rungs get climbed.
ai-security
Network Tapping for AI Verification: A Technical Assessment
Verifying what a compute cluster is doing might involve "tapping" the network — copying network packets for recomputation. These notes explore what it might take to do that.
ai-security
Understanding Data Center Power Delivery
We mapped the power delivery systems of AI data centers. Our diagram explores the data available at each stage, measurement techniques and signals of interest for AI security.
ai-security
Network Taps — A First Test
A quick test installation of a 10G network tap for AI verification — passive vs active taps, fibre types, and what scales to production speeds.
ai-security
The Tray as a Bandwidth Boundary
We used a DPU as a tray-level bandwidth limiter — an extra layer of security for protecting model weights, achieving near line-rate encryption with hardware-offloaded IPsec.