P020 Side-channel defences at scale

Can side-channel defences (shielding, filters, jamming, wardens) be mass-manufactured and retrofitted to cap a tray's leakage below a stated level, and at what unit cost?

Engineering side-channel defences (TEMPEST, filters, jamming, wardens) at scale.

Terms: TEMPEST: the standard body of techniques for shielding equipment so it does not leak information through stray electromagnetic emissions. wardens: monitors that watch for such leakage.

Status

Analyzed A paper design from a research sprint the author calls 'a first-pass viability study': enclosures, sensors, look-through jamming, inspections and physical security with an estimated bill of materials below 1% of cluster cost (this survey's cost goal of 1% of facility cost, met on paper only); power-filter volume cost 'has proven difficult' to pin down; no attenuation or leakage-rate cap measured; the 39 dB look-through suppression is cited from commodity radios in work not held; wardens: no work ('unexplored').

I present an example of a defense architecture towards the end of this post. It leverages a synergy of cheap enclosures, sensors, jamming, unannounced hardware inspections and physical security … at an estimated (!) Bill-of-Materials (BOM) below 1% of the cost of the monitored cluster
Cankaya (2026), Suppressing Side Channels in an Untrusted Data Center via Retrofitted Defenses (MIRI TGT blog) (2026-05-29), L62–65

Posed by

Also raised in: Cankaya (2026), A System Overview for Near-Term, Low-Trust AI Compute Verification (v0.2); Cankaya (2026), Research Note: The Fundamentals and Feasibility of Secure Network Taps for Verifying AI Datacenter Use; Cankaya (2026), Suppressing Side Channels in an Untrusted Data Center via Retrofitted Defenses (MIRI); Amodo (2026), AI 2040 Plan A — How You Can Help; Amodo (2026), AI 2040 Plan A — Verification SITREP.

Sub-questions

IDSub-questionWhat the sources report
P020.1Can tamper-evident, shielded enclosures or TEMPEST-proof trays be mass-manufactured and retrofitted onto a frontier cluster quickly, and what attenuation caps tray EM leakage below a stated leakage rate?open
P020.2What residual covert capacity per power cable remains after a TEMPEST filter plus continuous look-through (bps)?partly answered
P020.3What is the volume unit cost of a TEMPEST-grade filter for a rack power whip ($)?open
P020.4What self-interference suppression (dB) does continuous look-through jamming achieve on power-line and ultrasonic channels (39 dB shown only in commodity radios)?partly answered
P020.5What does an OEO isolation boundary per pretraining pod cost, as % of pod cost?partly answered
P020.6What does physical guarding and anti-bypass security cost relative to tap/enclosure BOM, and can anti-tamper assurance dispense with guards?implied by a source, not stated as open
P020.7Can an RF/power 'warden' detect a covert channel (at a stated rate) out of a GPU tray at a stated detection rate and false-alarm rate (targets to be agreed)?open

Possibly relevant work found by automated search

Found by AI agents searching for this problem's sub-questions, mostly by keyword and citation in the OpenAlex scholarly database and on the web; a second AI pass reviewed each one, and we spot-checked some by hand. They seemed reasonably related, as far as one can tell from outside each paper's field. Some come from neighbouring fields, such as arms control and financial audit, and bear on the problem by analogy. Not reviewed against the status above; a paper listed here does not change that status. 928 of 1052 quotes checked word for word against the paper's text.

For P020.1: Can tamper-evident, shielded enclosures or TEMPEST-proof trays be mass-manufactured and retrofitted onto a frontier cluster quickly, and what attenuation caps tray EM leakage below a stated leakage rate?

For P020.2: What residual covert capacity per power cable remains after a TEMPEST filter plus continuous look-through (bps)?

For P020.4: What self-interference suppression (dB) does continuous look-through jamming achieve on power-line and ultrasonic channels (39 dB shown only in commodity radios)?

For P020.5: What does an OEO isolation boundary per pretraining pod cost, as % of pod cost?

For P020.6: What does physical guarding and anti-bypass security cost relative to tap/enclosure BOM, and can anti-tamper assurance dispense with guards?

For P020.7: Can an RF/power 'warden' detect a covert channel (at a stated rate) out of a GPU tray at a stated detection rate and false-alarm rate (targets to be agreed)?

* Full text not reviewed; more likely to contain errors.

Data