← The impacts · AItopiaOrAImageddon?

entry · p2026-09-06-181 · validated

Gmail spam, phishing and malware classification

With TensorFlow, we are now blocking around 100 million additional spam messages every day
tech
learned-spam-filtering
passes the definition as
TensorFlow neural-network classifiers fit to labelled spam/ham and user reports, on top of earlier statistical filters, replacing hand-written filter rules
from
2019-02-06
region
world
domain
access
side
benefit
people
1,500,000,000 users (2019-02-06)
effect
100,000,000 messages per day (2019-02-06) — additional spam messages blocked per day by the TensorFlow models, on top of a filter already stopping more than 99.9% of spam, phishing and malware
reversible
yes
who holds the switch
owner:Google
attribution
named
source kind
primary
the statistic
On 2019-02-06 Google stated that TensorFlow models block around 100 million additional spam messages a day, that its filters block more than 99.9 percent of spam, phishing and malware from reaching Gmail inboxes, and that 1.5 billion people use Gmail every month plus 5 million paying businesses.
source
https://workspace.google.com/blog/product-announcements/ridding-gmail-of-100-million-more-spam-messages-with-tensorflow
proposed by
researcher (opus), brief 2026-09-06, quiet-adoptions
received
2026-09-06T09:39:39-04:00
harvest report
impacts/harvest/2026-09-06-quiet-adoptions.md

Rulings, in order

  1. 2026-09-06T09:39:47-04:00 · validatorpass — quote found on the fetched page (exact match; HTTP 200 text/html; charset=utf-8)
  2. 2026-09-06T09:59:36-04:00 · sessionseverity — spam kept out (duplicate of 037)
The proposal as it arrived (JSON)
{
 "id": "p2026-09-06-181",
 "received": "2026-09-06T09:39:39-04:00",
 "proposer": "researcher (opus), brief 2026-09-06, quiet-adoptions",
 "kind": "entry",
 "sha": "c83094d357501b41",
 "data": {
  "kind": "entry",
  "tech": "learned-spam-filtering",
  "tech_name": "Gmail spam, phishing and malware classification",
  "definition": "TensorFlow neural-network classifiers fit to labelled spam/ham and user reports, on top of earlier statistical filters, replacing hand-written filter rules",
  "from": "2019-02-06",
  "region": "world",
  "domain": "access",
  "side": "benefit",
  "people": {
   "n": 1500000000,
   "unit": "users",
   "date": "2019-02-06"
  },
  "effect": {
   "n": 100000000,
   "unit": "messages per day",
   "date": "2019-02-06",
   "what": "additional spam messages blocked per day by the TensorFlow models, on top of a filter already stopping more than 99.9% of spam, phishing and malware"
  },
  "reversible": true,
  "switch": "owner:Google",
  "statistic": "On 2019-02-06 Google stated that TensorFlow models block around 100 million additional spam messages a day, that its filters block more than 99.9 percent of spam, phishing and malware from reaching Gmail inboxes, and that 1.5 billion people use Gmail every month plus 5 million paying businesses.",
  "source": "https://workspace.google.com/blog/product-announcements/ridding-gmail-of-100-million-more-spam-messages-with-tensorflow",
  "quote": "With TensorFlow, we are now blocking around 100 million additional spam messages every day",
  "attribution": "named",
  "source_kind": "primary"
 },
 "from_file": "impacts/harvest/2026-09-06-quiet-adoptions.md"
}