Korean carriers' intelligent spam blocking stops 97.7% of test spam

In test sends by Korea's regulator, the three mobile carriers' free intelligent spam filters blocked 97.7% of illegal spam texts in the second half of 2022, up from 89.5% in late 2019.

  • 2 for a person

    In the regulator's test sends, the free filters blocked 97.7% of illegal spam texts in the second half of 2022, up from 89.5% in the second half of 2019.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

Three independent regulatory documents support the benefit.

Compared with

The same services' average blocking rate in the second half of 2019. Measured.

Without the system
89.5%
With it
96.2% in the first half of 2020
The system’s part
Not isolated. The Commission measured each carrier's service as a whole, with no comparison of filtering with and without machine learning. The releases do not describe how the filters work. The Commission credited the 2019 rise to spam-information sharing among the carriers. It reported in February 2024 that KT had recently introduced AI-based filtering, so the filters tested from 2019 to 2022 may not all have used machine learning.
Later
Challenged, 5 April 2024. The Commission reported that illegal spam texts received per person rose in the second half of 2023 and wrote that the carriers should strengthen the filtering of their intelligent (AI) spam blocking services.
Not yet checked
LimitsCosts and harmsLearns from data

Download data Cite Suggest a correction

Benefit type
Increased Product Safety
System
Intelligent spam blocking services (지능형 스팸차단 서비스) of SK Telecom, KT and LG U+
Made by
SK Telecom, KT and LG Uplus
Used by
SK Telecom, KT and LG Uplus (free service for subscribers)
Where
South Korea (nationwide mobile networks)
Stage
In routine use
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Identifying Objects, Actions, and Events, Monitoring Processes, Materials, or Surroundings
Collections
Scrutiny and findings
Last revised
1 November 2026

Sources

  1. Regulatory document, by authors with no tie to the system.

    Korea Communications Commission (방송통신위원회) and Korea Internet & Security Agency. 휴대전화 음성스팸 줄고, 문자스팸 늘어 [Voice spam on mobile phones falls, text spam rises], press release on the survey of spam in the second half of 2022 (「2022년 하반기 스팸 유통현황」), 31 March 2023.

    한편, 이동통신사의 문자스팸 차단율 조사는 이통3사가 무료로 제공 중인 '지능형 스팸차단 서비스*'의 문자스팸 차단율을 측정하는 것으로, '22년 하반기 차단율은 평균 97.7%로 전기 대비 0.8%p 상승한 수치로 나타났다.

  2. Regulatory document, by authors with no tie to the system.

    Korea Communications Commission (방송통신위원회) and Korea Internet & Security Agency. 방통위, 「2020년 상반기 스팸 유통현황」 조사 결과 발표 [The Commission announces its survey of spam in the first half of 2020], press release, 29 September 2020.

    이통3사의 '지능형 스팸차단서비스' 차단율을 조사한 결과, 문자스팸 차단율은 평균 96.2%로 '19년 하반기 대비 6.7%p 증가(89.5%→96.2%)한 것으로 나타났다.

  3. Regulatory document, by authors with no tie to the system.

    Korea Communications Commission (방송통신위원회). 스팸 10건 중 9건은 막는다...문자스팸 차단율 89.5% [Nine in ten spam texts blocked, text spam blocking rate 89.5%], press release on the survey of spam in the second half of 2019 (「2019년 하반기 스팸 유통현황」), 25 March 2020.

    2019년 하반기 총 26주 동안 스팸 문자메시지를 전송한 후 이동통신사의 문자스팸 차단율을 측정한 결과, 10건 중 평균 9건(차단율 89.5%)*을 차단해 주는 것으로 나타났다.

  4. Regulatory document, by authors with no tie to the system. Context or contrary evidence.

    Korea Communications Commission (방송통신위원회) and Korea Internet & Security Agency. 방통위, 「2023년 하반기 스팸 유통현황」 발표 [The Commission announces its survey of spam in the second half of 2023], press release, 5 April 2024.

    각 이동통신사에서도 '지능형(AI) 스팸차단서비스'의 스팸 필터링 정책 강화와 차단성능 개선 등 불법스팸의 실질적 차단율 향상에 노력을 더욱 기울여야 할 것으로 분석된다.

  5. Regulatory document, by authors with no tie to the system. Context or contrary evidence.

    Korea Communications Commission (방송통신위원회). 방통위(이상인 부위원장), 국민생활 불편을 야기하는 불법스팸 차단을 위해 이동통신사(KT) 현장점검 [The Commission's vice chairman inspects KT's blocking of illegal spam], press release, 20 February 2024.

    이날 최근 도입한 인공지능(이하 'AI') 기반 스팸 필터링 기술을 시연하고 적극적인 노력을 통해 스팸신고 비중을 줄이고 있다고 밝혔다.

Details

AI system

Workflow

The three carriers provided the blocking service to subscribers free of charge. From October 2019 the carriers shared spam information with one another, under a policy agreed with the Commission.

Follow-up

Conditions for replication

The filters must keep up with spam that changes to get around blocking systems. The carriers must keep strengthening their filtering policies and blocking performance.

Entry details

Sector

Telecommunications / spam and fraud prevention.

Purpose

SK Telecom, KT and LG Uplus built their intelligent spam blocking services to filter spam text messages for subscribers free of charge.

31 more questions not yet checked

model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). Korean carriers' intelligent spam blocking stops 97.7% of test spam (AIBD-1004). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1004.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions