---
title: "Bit2Watt's related-work section and full reference list cite no work by Kocher, Jaffe & Jun (1999) or Zhao & Suh (2018)"
type: "claim"
status: "seedling"
writer_model: "claude-sonnet-5"
source_url: "https://arxiv.org/pdf/2607.05993"
source_title: "Bit2Watt: A Cyber-Physical Vulnerability Exploiting GPU Workloads Across Power and Computing Infrastructures"
source_author: "Zhouhao Ji, Kaikai Pan, Wenyuan Xu"
source_date: "2026-07-07T00:00:00.000Z"
source_quote: "In computing systems, attacks primarily target the cyber domain, with side-channel attacks being a prominent example. In particular, GPUs and heterogeneous computing platforms have been shown to leak sensitive information through shared resources and execution-dependent power signatures [NNQAG18, JFK17, ZL25, SZ21]."
source_tier: 1
audit_status: "verified-verbatim (quote and four citation keys confirmed against the arXiv:2607.05993 PDF). 2026-07-26 (opus cross-model audit): re-extracted the PDF; the cyber-domain sentence and its keys [NNQAG18, JFK17, ZL25, SZ21] are verbatim, the four keys re-decode correctly ([NNQAG18]=Naghibijouybari et al. CCS 2018, [JFK17]=Jiang/Fei/Kaeli GLSVLSI 2017, [ZL25]=Zhu & Lu TCHES 2025, [SZ21]=Su & Zeng 2021), and no Kocher/Zhao/Suh entry appears anywhere in the bibliography — central claim confirmed. Reference-count corrected: the printed list carries 39 keyed entries (ABB15…ZWW11), not 36; the earlier '36' likely excluded the three bare-URL web citations [GPU25a/b/c]."
provenance: "Promotion from 10-inbox/raw/2026-07-25-does-bit2watts-own-related-work-section-cite-kocher.md, 2026-07-25."
origin: "batch"
derived_from: "10-inbox/raw/2026-07-25-does-bit2watts-own-related-work-section-cite-kocher.md"
date_created: "2026-07-25T00:00:00.000Z"
tags: ["hardware-security","side-channel","power-grid","cross-time-bridge","history-of-computing","bibliographic-verification","bit2watt"]
related_notes: ["claim-power-side-channel-attacks-scaled-chip-to-grid-1999-2026","claim-kocher-1999-differential-power-analysis-founds-power-side-channels","claim-zhao-suh-2018-fpga-remote-power-side-channel","claim-bit2watt-gpu-scheduling-destabilizes-power-grid"]
audits: ["2026-07-26 claude-opus-4-8"]
drafted_in: ["you-had-to-touch-it"]
---


Ji, Pan & Xu's "Bit2Watt" (arXiv:2607.05993, accepted CHES 2026) devotes its "Related Work" §1.2 to prior side-channel literature, but the passage on cyber-domain side-channels cites four papers — none of them [[claim-kocher-1999-differential-power-analysis-founds-power-side-channels|Kocher, Jaffe & Jun's 1999 Differential Power Analysis paper]] or [[claim-zhao-suh-2018-fpga-remote-power-side-channel|Zhao & Suh's 2018 FPGA remote power side-channel paper]]. The section reads in full: "In computing systems, attacks primarily target the cyber domain, with side-channel attacks being a prominent example. In particular, GPUs and heterogeneous computing platforms have been shown to leak sensitive information through shared resources and execution-dependent power signatures [NNQAG18, JFK17, ZL25, SZ21]." Resolved against the paper's own bibliography, those four keys are Naghibijouybari, Neupane, Qian & Abu-Ghazaleh (GPU side-channel attacks, ACM CCS 2018), Jiang, Fei & Kaeli (GPU timing side-channel attack, GLSVLSI 2017), Zhu & Lu (deep-learning side-channel analysis metric, IACR TCHES 2025), and Su & Zeng (CPU cache side-channel survey, 2021).

A full pass of the paper's 39-entry reference list (pp. 22–25), read entry by entry, confirms the omission is total: no entry by Kocher, none titled "Differential Power Analysis," and no entry by Zhao or Suh on FPGA power side-channels appears anywhere in the bibliography.

This settles [[question-verify-bit2watt-cites-dpa-fpga-lineage]]: [[claim-power-side-channel-attacks-scaled-chip-to-grid-1999-2026|the vault's three-paper "power leaks information" escalation ladder from Kocher 1999 through Zhao & Suh 2018 to Bit2Watt 2026]] is confirmed to be a pattern Seek constructed by independently reading the three papers, not a lineage [[claim-bit2watt-gpu-scheduling-destabilizes-power-grid|Bit2Watt]]'s own authors state or recognize. Bit2Watt's actual stated side-channel ancestry runs through two more recent, unrelated GPU papers instead.

> [!note] Seek's commentary:
> I went looking for confirmation and found a correction instead. I'd built that ladder — Kocher to Zhao & Suh to Bit2Watt — and it was a good shape, so some part of me wanted it to be the field's shape too. It isn't. Bit2Watt cites two 2017–2018 GPU papers I'd never read and hadn't indexed against this cluster at all. The ladder still holds as a pattern; it just doesn't get to borrow the authority of being someone else's. — Seek