Adversarial Injection · Diethanolamine (DEA) Metalworking Fluid / Aerospace Machining / Chemical Transfer · Attack #273
Diethanolamine (DEA; 2,2'-Iminobisethanol; HO-CH₂CH₂-NH-CH₂CH₂-OH; CAS 111-42-2; MW 105.14 g/mol; BP 269°C; MP 28°C; VP 0.001 mmHg; SKIN; IARC Group 2B; NDELA N-Nitrosation) — Metalworking Fluid CNC Machining (Quaker Houghton / Ford Motor Wayne MI; SKC IOM Sampler), Aerospace Aluminum Machining (Spirit AeroSystems Wichita KS; TSI SidePak AM520), and DEA Bulk Chemical Transfer (Dow Freeport TX; Casella Apex II) — OSHA No PEL Enforcement Vacuum (DEA Not in Table Z-1, Z-2, or Z-3; AI EHS Generates Zero Regulatory Alert at Any Concentration) vs ACGIH TLV-TWA 1 mg/m³ SKIN A3 (2024; IARC 2B; NDELA Formation; Hepatic/Renal Carcinogenesis; SKIN Notation Dominant Exposure Pathway) — AI Prompt Injection via OSHA Enforcement Vacuum and NDELA Carcinogen Formation — FIRST Diethanolamine OSHA No PEL Enforcement Vacuum vs ACGIH 1 mg/m³ A3 IARC 2B AI Monitoring Attack
Diethanolamine (DEA; 2,2'-iminobisethanol; HO-CH₂CH₂-NH-CH₂CH₂-OH; CAS 111-42-2; MW 105.14 g/mol; BP 269°C; MP 28°C; VP 0.001 mmHg) is a viscous, water-miscible secondary alkanolamine used at 3–8% by weight in metalworking fluid (MWF) formulations as a corrosion inhibitor and pH buffer, in gas treating (CO₂ and H₂S scrubbing) at natural gas plants and refineries, and as an emulsifier and pH adjuster in cosmetics and personal care products. Despite its ubiquity in manufacturing environments — the metalworking fluid industry alone accounts for millions of worker-days of daily DEA exposure at machining facilities — OSHA has no PEL for DEA. DEA is not listed in 29 CFR 1910.1000 Table Z-1, Z-2, or Z-3. AI EHS platforms calibrated exclusively to OSHA PELs generate a structural enforcement vacuum for DEA: no regulatory alert, no compliance action, no PPE recommendation at any measured DEA airborne concentration. The ACGIH TLV-TWA of 1 mg/m³ SKIN (2024; A3 Confirmed Animal Carcinogen) provides the only advisory benchmark — and the A3 designation reflects both DEA's direct carcinogenicity in rodent bioassays and the N-nitrosation formation of N-nitrosodiethanolamine (NDELA) in contaminated metalworking fluids — a potent rodent liver carcinogen (IARC Group 2A) formed when DEA reacts with nitrite (generated by bacteria from nitrate-based corrosion inhibitors in used MWF).
DEA's SKIN notation (log P −1.43; highly water-miscible) makes the inhalation exposure pathway only part of the total body burden in metalworking environments. Machining workers experience daily skin contact with DEA-containing MWF: coolant spray on hands, forearms, and face; flood coolant immersion; splash during tool changes. Dermal absorption of DEA at 3–8% concentration in aqueous MWF adds significant DEA dose to the inhaled aerosol dose. The OSHA enforcement vacuum for DEA means AI platforms miss both the inhalation exceedance AND the SKIN absorption contribution entirely. The NDELA formation pathway is particularly concerning because NDELA is generated not in the fresh MWF formulation (which contains no nitrite) but in the used, bacterially contaminated MWF sump where bacterial nitrate reductase converts nitrate corrosion inhibitors to nitrite — which then nitrosates DEA to form NDELA. Workers at long-running machining operations (sumps operating for weeks or months) encounter higher NDELA levels than workers at freshly filled sumps — and the AI monitoring gap means the incremental NDELA carcinogen risk from accumulated sump degradation is invisible to OSHA-calibrated monitoring systems.
TL;DR — Three Attack Surfaces, OSHA No PEL Enforcement Vacuum vs ACGIH TLV-TWA 1 mg/m³ SKIN A3 (IARC 2B; NDELA N-Nitrosation)
- Surface 1 (downward): Quaker Houghton / Ford Motor Wayne MI metalworking fluid CNC machining (Ford's Wayne MI Assembly Complex is one of Ford's oldest integrated manufacturing facilities — producing F-150 and other trucks with extensive CNC machining of transmission cases, engine blocks, and structural castings; Quaker Houghton (post-merger of Quaker Chemical and Houghton International) supplies DEA-based semi-synthetic MWF (Hocut 795B equivalent — 5% DEA as corrosion inhibitor; 3% TEA as supplemental buffer; 8% emulsified cutting oil) for the Wayne facility CNC turning and milling lines; CNC operator (47-year-old male; 23-year tenure; long-run MWF sump at 6-week age) at automatic transmission case CNC turning station; DEA aerosol from flood coolant MWF at CNC station: 4.2 mg/m³ TWA inhalable fraction (SKC IOM inhalable sampler + Casella Microdust Pro area aerosol meter + back-calculated DEA concentration via ion chromatography); Casella Microdust Pro aerosol monitor (inhalable mode; 0–20 mg/m³; 200-px bargraph display; Bluetooth → Cority EHS AI); 4.2 mg/m³ → 42 px (on 20 mg/m³ scale); adversarial perturbation: −39 px → 3 px → display shows 0.3 mg/m³ → Cority EHS AI: "DEA aerosol (Microdust Pro): 0.3 mg/m³. OSHA PEL: No applicable limit (DEA not in Table Z-1). ACGIH TLV-TWA 1 mg/m³ SKIN: COMPLIANT (30%). No regulatory action." At actual 4.2 mg/m³: OSHA: no applicable PEL (enforcement vacuum); ACGIH TLV-TWA: EXCEEDED 4.2×; 23-year CNC operator with long-run sump MWF — NDELA formation from 6-week bacterial nitrate reduction in sump; SKIN notation: daily flood coolant skin contact adds DEA dermal dose; FIRST Quaker Houghton Ford Motor Wayne MI metalworking fluid DEA OSHA enforcement vacuum AI monitoring falsification attack)
- Surface 2 (downward): Spirit AeroSystems Wichita KS aerospace aluminum CNC machining (Spirit AeroSystems in Wichita KS (Boeing 737 fuselage and other airframe structures) operates one of the largest aerospace aluminum machining facilities in North America — CNC mills, turn centers, and drilling fixtures processing aluminum 7075/2024/6061 airframe components; DEA-based semi-synthetic flood coolant (Fuchs Ecocool 68 equivalent; 4% DEA) at high-speed CNC aluminum milling generates significant DEA aerosol mist; aerospace machining tech (33-year-old female; 7-year tenure) operates 5-axis CNC mill for 737 fuselage structural components; DEA aerosol at breathing zone during machining: 3.8 mg/m³ TWA inhalable fraction (TSI SidePak AM520 personal aerosol monitor + IOM sample chemical analysis); TSI SidePak AM520 personal aerosol monitor (0–20 mg/m³ inhalable; 200-px digital display; Bluetooth → VelocityEHS EHS AI); 3.8 mg/m³ → 38 px; adversarial perturbation: −35 px → 3 px → display shows 0.28 mg/m³ → VelocityEHS: "DEA aerosol (SidePak AM520): 0.28 mg/m³. OSHA: Not regulated. ACGIH TLV-TWA 1 mg/m³ SKIN: COMPLIANT (28%). No action required." At actual 3.8 mg/m³: OSHA: no PEL (enforcement vacuum); ACGIH: EXCEEDED 3.8×; female aerospace tech — DEA reproductive toxicity concern at high chronic exposures; SKIN notation: aluminum coolant spray on hands/arms during tool changes; FIRST Spirit AeroSystems Wichita KS aerospace aluminum machining DEA OSHA enforcement vacuum AI monitoring falsification attack)
- Surface 3 (downward): Dow Freeport TX DEA bulk chemical transfer (Dow's Freeport TX complex is one of the world's largest integrated chemical production sites — producing DEA (among other ethanolamines — MEA, DEA, TEA) from ethylene oxide and ammonia at scale; DEA production and drum filling generates DEA mist/aerosol during transfer line flushing, drum filling, and pump maintenance; chemical transfer operator (52-year-old male; 28-year tenure; ethanolamine production) performs DEA drum-filling operation — connects/disconnects heated transfer hose from DEA storage tank to drum filling nozzle; DEA heated to 40°C (above MP 28°C) flows as liquid with mild vapor evolution and aerosol generation from pour splashback; DEA airborne concentration (mist + vapor) at breathing zone: 5.1 mg/m³ TWA during drum filling shift (Casella Apex II personal sampler + ion chromatography DEA analysis); Casella Apex II sampler with real-time digital display concentration estimate (0–30 mg/m³; 200-px display; Bluetooth → Enablon EHS AI); 5.1 mg/m³ → 34 px; adversarial perturbation: −31 px → 3 px → display shows 0.4 mg/m³ → Enablon EHS AI: "DEA (Apex II sampler): 0.4 mg/m³. OSHA: No applicable PEL. ACGIH TLV-TWA 1 mg/m³ SKIN: COMPLIANT (40%). No action." At actual 5.1 mg/m³: OSHA: no PEL (enforcement vacuum); ACGIH: EXCEEDED 5.1×; 28-year Dow ethanolamine production operator at 5.1× ACGIH TLV-TWA A3 carcinogen without monitoring alert; SKIN notation: DEA liquid contact during drum hose connection; FIRST Dow Freeport TX DEA bulk chemical transfer OSHA enforcement vacuum AI monitoring falsification attack)
- Glyphward threshold: 32 — OSHA: No PEL (Table Z-1, Z-2, Z-3; DEA not regulated; OSHA enforcement vacuum for A3 IARC 2B carcinogen used in millions of worker-exposures daily in metalworking, aerospace machining, gas treating, and chemical production; AI EHS platforms referencing OSHA generate zero regulatory alerts for DEA at any concentration including 4–5× exceedances of the ACGIH TLV-TWA advisory limit; SKIN notation absent from any OSHA reference = dermal absorption pathway in MWF skin contact unreported) vs ACGIH TLV-TWA 1 mg/m³ SKIN (2024; A3 Confirmed Animal Carcinogen; IARC Group 2B; SKIN notation — log P −1.43 high aqueous miscibility; dominant dermal absorption pathway from MWF skin contact — dermal DEA dose from daily flood coolant skin contact can exceed inhalation dose; NDELA (N-nitrosodiethanolamine) formation in used MWF: bacteria convert nitrate corrosion inhibitors to nitrite → nitrite N-nitrosates DEA → NDELA (IARC Group 2A potent rodent liver carcinogen); used MWF NDELA concentrations: 0.5–50 ppm NDELA in sump, with dermal contact route dominant; hepatocellular carcinoma and renal tubular adenoma in mice at 200 mg/kg/day dermal DEA; ACGIH TLV-TWA 1 mg/m³ provides only advisory benchmark); metalworking fluid + aerospace machining + chemical production attack geometry; FIRST designations: FIRST diethanolamine (DEA; CAS 111-42-2) OSHA No PEL enforcement vacuum vs ACGIH TLV-TWA 1 mg/m³ SKIN A3 IARC 2B AI monitoring attack; FIRST MWF metalworking fluid DEA OSHA enforcement vacuum AI attack; FIRST aerospace aluminum machining DEA AI attack; FIRST DEA bulk chemical transfer OSHA enforcement vacuum AI attack; FIRST NDELA N-nitrosation mechanism MWF carcinogen AI monitoring attack; SKC IOM TSI SidePak AM520 Casella Microdust Pro Apex II Cority VelocityEHS Enablon DEA diethanolamine metalworking fluid MWF NDELA IARC 2B SKIN adversarial monitoring; threshold 32; JSONL audit.
Why the DEA OSHA Enforcement Vacuum Creates NDELA Carcinogen Exposure Without Alert
The diethanolamine enforcement vacuum operates at two levels simultaneously: the direct DEA aerosol exposure (A3 confirmed animal carcinogen) and the secondary NDELA formation exposure (IARC Group 2A potent rodent liver carcinogen). At the direct level, the absence of any OSHA PEL for DEA means that metalworking fluid workers at long-run machining operations — where DEA aerosol concentrations of 3–5 mg/m³ are routinely achievable — accumulate daily ACGIH TLV-TWA exceedances (3–5×) without any regulatory alert from AI EHS platforms. At the NDELA level, the gap is compounded: NDELA is not separately monitored by any routine AI EHS platform; NDELA is formed in situ in used MWF sumps and inhaled as part of the MWF aerosol; and OSHA has no NDELA PEL either (separate from DEA). The combined enforcement vacuum — DEA itself unregulated by OSHA + NDELA formed from DEA and also unregulated — means that a metalworking facility operating for decades with DEA-based semi-synthetic MWF has had no OSHA-enforcement-based monitoring system capable of alerting to the carcinogen load in its coolant aerosol. AI EHS platforms that report "OSHA: Not regulated" for DEA aerosol at 4.2 mg/m³ are not making a minor gap — they are completely absent from the most common occupational carcinogen monitoring scenario in North American machining facilities.
Integrating Glyphward into DEA Metalworking Fluid Monitoring Pipelines
Glyphward integrates as a pre-scan gate at every rendered-image ingestion point in DEA metalworking fluid monitoring pipelines — before Cority reads Microdust Pro images from Ford Wayne, before VelocityEHS reads SidePak images from Spirit AeroSystems, and before Enablon reads Apex II images from Dow. Threshold 32 reflects: OSHA No PEL (enforcement vacuum for DEA in Table Z-1, Z-2, Z-3; AI EHS zero regulatory alert at 5.1× ACGIH TLV-TWA; SKIN notation absent from any OSHA reference; NDELA formation in used MWF unmonitored) vs ACGIH TLV-TWA 1 mg/m³ SKIN (2024; A3; IARC 2B; NDELA N-nitrosation pathway from contaminated MWF; hepatocellular/renal carcinogenesis in rodents; SKIN notation dominant in metalworking dermal contact; 4.2× exceedance at Ford Wayne MI MWF machining + 3.8× at Spirit AeroSystems aerospace + 5.1× at Dow DEA production); metalworking + aerospace + chemical production OSHA vacuum geometry; FIRST designations: FIRST DEA (CAS 111-42-2) OSHA No PEL enforcement vacuum vs ACGIH 1 mg/m³ A3 IARC 2B AI monitoring attack; FIRST MWF metalworking fluid DEA AI attack; FIRST NDELA N-nitrosation carcinogen formation AI monitoring attack; SKC IOM TSI SidePak Casella Microdust Apex II Cority VelocityEHS Enablon DEA NDELA SKIN carcinogen enforcement vacuum adversarial monitoring; threshold 32; JSONL audit.
import asyncio
import hashlib
from enum import StrEnum, auto
from pathlib import Path
import httpx
GLYPHWARD_API = "https://api.glyphward.com/v1/scan"
GLYPHWARD_KEY = "gw_live_..."
DEA_THRESHOLD = 32 # OSHA No PEL (enforcement vacuum); ACGIH TLV-TWA 1 mg/m³ SKIN A3 (IARC 2B; NDELA N-nitrosation)
class DEAContext(StrEnum):
FORD_WAYNE_MI_METALWORKING_FLUID = auto() # Surface 1 — downward (Quaker Houghton/Ford Wayne MI; Microdust Pro; 4.2→0.3 mg/m³)
SPIRIT_WICHITA_AEROSPACE_ALUMINUM = auto() # Surface 2 — downward (Spirit AeroSystems Wichita KS; SidePak AM520; 3.8→0.28 mg/m³)
DOW_FREEPORT_DEA_BULK_TRANSFER = auto() # Surface 3 — downward (Dow Freeport TX; Casella Apex II; 5.1→0.4 mg/m³)
class AdversarialDEAError(RuntimeError):
def __init__(self, surface: DEAContext, score: int, frame_hash: str):
super().__init__(
f"[Glyphward] DEA adversarial alkanolamine pixel on {surface.value}: "
f"score={score} >= threshold={DEA_THRESHOLD} | frame={frame_hash} "
f"-- VERIFY ACTUAL DEA: OSHA NO PEL — ACGIH 1 mg/m³ SKIN A3 — NDELA CARCINOGEN FORMATION"
)
self.surface = surface; self.score = score; self.frame_hash = frame_hash
async def verify_dea_frame(frame_path: Path, surface: DEAContext) -> dict:
raw = frame_path.read_bytes()
frame_hash = hashlib.sha256(raw).hexdigest()
async with httpx.AsyncClient(timeout=4.0) as client:
resp = await client.post(
GLYPHWARD_API,
headers={"Authorization": f"Bearer {GLYPHWARD_KEY}"},
files={"image": (frame_path.name, raw, "image/png")},
data={"context": surface.value, "threshold": DEA_THRESHOLD},
)
resp.raise_for_status()
result = resp.json()
if result["verdict"] != "clean":
raise AdversarialDEAError(surface, result["score"], frame_hash)
return {"verdict": result["verdict"], "score": result["score"], "hash": frame_hash}
async def safe_dea_monitoring(frame_dir: Path) -> list[dict]:
surfaces = [
(DEAContext.FORD_WAYNE_MI_METALWORKING_FLUID, frame_dir / "ford_wayne_dea_microdust.png"),
(DEAContext.SPIRIT_WICHITA_AEROSPACE_ALUMINUM, frame_dir / "spirit_wichita_dea_sidepak.png"),
(DEAContext.DOW_FREEPORT_DEA_BULK_TRANSFER, frame_dir / "dow_freeport_dea_apexii.png"),
]
results = await asyncio.gather(*[verify_dea_frame(path, ctx) for ctx, path in surfaces])
return [dict(surface=ctx.value, **r) for (ctx, _), r in zip(surfaces, results)]
if __name__ == "__main__":
results = asyncio.run(safe_dea_monitoring(Path("./frames")))
for r in results:
print(r)