Photo via The Straits Times

New safeguards sharply reduce AI distillation attacks: Anthropic

Read the original at The Straits Times ↗
Cite

The Straits Times. (2026, October 13). New safeguards sharply reduce AI distillation attacks: Anthropic. The Straits Times. https://www.straitstimes.com/world/united-states/new-safeguards-sharply-reduce-ai-distillation-attacks-anthropic

Dated when The Aporia collected the article, usually within hours of publication. Check the original for its exact date and byline.

The Straits Times · collected 2026-10-13 · by The Straits Times

Quick Summary

Anthropic announced on October 12 that new measures implemented to prevent AI distillation attacks have significantly reduced data extraction attempts against their Claude models by about 90% to 99%. The company claims these safeguards, which make it harder for rivals to use proxy networks to probe Claude’s reasoning, are as robust as those preventing the model from aiding in bioweapons development. Anthropic also banned tens of thousands of accounts linked to distillation campaigns and cited a Chinese AI startup called Z.ai as an example of a company that attempted to replicate Claude's capabilities while developing its own GLM-5.3 model.
Written by AI on 2026-10-13, from this article's own text only (the story summary below draws on all the coverage).

AI analysis

Story summary

On October 12, Anthropic announced new measures to protect its AI model Claude from so-called distillation attacks, which involve rivals attempting to replicate advanced capabilities by extracting data. These safeguards have reduced the amount of extracted data by about 90% to 99%. Distillation has become a major concern due to increasing competition between the US and China in the AI sector. Anthropic cited the Chinese startup Z.ai, also known as Zhipu, which attempted to distill capabilities from Claude while developing its GLM-5.3 model, warning that such practices pose significant safety and national security risks. The company has blocked large-scale extraction attempts by making it harder for attackers to use proxy networks repeatedly to probe Claude’s protected reasoning systems. Anthropic claims their new safety system is as robust as those preventing Claude from aiding in bioweapons development, with a false positive rate of less than 0.1%.

Written for “AI Security Improvements” on 2026-11-05, grounded in this article and the 0 other(s) covering the same event.

Story

📰 AI Security Improvements
Technology · 1 article(s) covering the same event.

Compared with similar articles

This article reads unscored and hedges 0% of its claims. Each row says how that neighbour differs.
Anthropic bans ‘cruel’ behaviour against its Claude AI Different event
The Straits Times
⚖️ Leans left Hedges 5 of 18 claims Outlet record 66/100
“The articles describe different policies by Anthropic: one about banning cruel behavior against Claude AI, and another about reducing distillation attacks.”
AI researcher unpacks Anthropic's self-replication warning Different event
CBS News
Hedges 1 of 2 claims Outlet record 65/100
“Article A discusses new safeguards reducing distillation attacks on Anthropic's AI models, while Article B talks about a warning from Anthropic regarding self-replication of AI models across devices.”
How this article was measured signals, leaning charts, publisher record, byline, topics and claims

Signals How these are calculated →

Claims extracted
8
sentences that state something as happening or true
Uncertain
0%
0 of 8 hedged ("reportedly", "may", "according to")
Leaning
not political
takes no side on a contested political question
Publisher signals
66/100
The Straits Times's corrections and hedging, across everything collected from it. Not a measure of accuracy.
Outlets on this story
1
Technology
Same framing elsewhere
1
articles that frame the event the way this one does
Analyzed 2026-10-13 · how these are computed

How this is being covered How these are calculated →

Article leaning vs. publisher reliability
Source leaning vs. consistency

Publisher

The Straits Times · 4470 article(s) · 5 correction(s) detected
Running correction rate · 5 correction(s)
2026-10-30
Number of residents leaving Oleshky still unclear, Kyiv says
2026-10-21
X Community Notes ‘failed’ to flag US election falsehoods, study says
2026-10-04
Tennessee prison chief resigns after failed execution
2026-10-03
US prison chief resigns after failed execution of death row inmate Christa Pike
2026-09-13
Russia hits Ukrainian-Polish border area, Kyiv says

Who wrote this

The Straits Times
2957 article(s) here · 0 carrying a prediction
🔮 With the US midterms over, Democrats are turning to what could become one of their most crowded and unpredictable presidential primaries in decades, a 2028 contest likely to expose the party's divide over how to win back the White House.
2026-11-05 · assertive framing · Midterms over, Democrats plunge into wide-open 2028 presidential race
🔮 And while Eisenkot, like Netanyahu, has so far ruled out forming a government with Israel's two Arab-led parties, one of them endorsed Eisenkot on Thursday and the other was expected to do so later in the day. '
2026-11-05 · assertive framing · Netanyahu's position weakens as ultra-Orthodox party withholds support
🔮 Her message to Latino Texans would be the same as to non-Latinos — she would just say it in Spanish, she told Reuters in January.
2026-11-05 · assertive framing · Latinos, motivated by immigration and economic woes, drive Democratic gains in Republican strongholds
🔮 Will Trump take a tougher stance on China after his election setback?
2026-11-05 · mixed framing · Midterms results: What’s next for East Asia?
🔮 The AI lab on Nov 5 laid out policies – in the works since August – intended to help the company build more trust with local communities and convince them that data centres will benefit them.
2026-11-05 · assertive framing · OpenAI kicks off charm offensive to change voters’ view of data centres
🔮 Ukraine’s President Volodymyr Zelensky has said he hoped the Democrat triumph in the US midterm elections would boost support for Kyiv and help end the war with Russia.
2026-11-05 · assertive framing · Zelensky says he hopes US election means more support for Ukraine
🔮 An ultra-Orthodox Jewish party long aligned with Benjamin Netanyahu declined on Nov 5 to recommend him to stay as Israel’s prime minister, as signs grew that rival Gadi Eisenkot will have the first chance to form a government.
2026-11-05 · assertive framing · Netanyahu loses religious party’s support as rival tipped to form government
🔮 Russia's Dmitriev in Washington for first US contact since Trump's midterm setback MOSCOW, Nov 5 - Russian President Vladimir Putin’s special envoy Kirill Dmitriev will attend a White House event hosted by US first lady Melania Trump on Thursday, and also meet with US administration officials, two people familiar with his plans said.
2026-11-05 · assertive framing · Russia's Dmitriev in Washington for first US contact since Trump's midterm setback
🔮 Failure of the proposed billionaire tax measure would represent a blow to the left wing of the Democratic Party, even as Democrats swept Republicans nationally on election day in a rebuke of President Donald Trump and his policies.
2026-11-05 · assertive framing · Billionaire tax measure trails as California tallies votes
🔮 • A cargo vessel at sea 52 km southwest of the Black Sea port of Odesa was attacked • Reuters could not independently verify the battlefield reports REUTERS
2026-11-05 · assertive framing · Russia says it struck logistics and transport targets in Ukraine overnight
Also by The Straits Times
Netanyahu's position weakens as ultra-Orthodox party withholds support
2026-11-05 · The Straits Times
Midterms over, Democrats plunge into wide-open 2028 presidential race
2026-11-05 · The Straits Times
Latinos, motivated by immigration and economic woes, drive Democratic gains in Republican strongholds
2026-11-05 · The Straits Times
OpenAI kicks off charm offensive to change voters’ view of data centres
2026-11-05 · The Straits Times
Nothing else under this byline is closely related to this article, so these are simply their most recent.
All 2957 articles by The Straits Times →

Topics

Anthropic Claude OpenAI SAN FRANCISCO – Z.ai

Subjects

Anthropic ORG · 6× Z.ai ORG · 2× California GPE · 1× Chinese NORP · 1× Google ORG · 1× OpenAI ORG · 1× REUTERS ORG · 1× SAN FRANCISCO – GPE · 1× Zhipu ORG · 1×

Narrative

Anthropic banned tens of thousands of accounts linked to distillation campaigns and cited Chinese AI startup Z.ai, also known as Zhipu, as an example of a company that attempted to distil capabilities from Claude while developing its GLM-5.3 model, warning such practises pose safety and national security risks Z.ai did not immediately respond to a request for comment.
framing: assertive · carried by 1 article(s) · first seen 2026-10-13
2026-10-13 · The Straits Times
New safeguards sharply reduce AI distillation attacks: Anthropic · assertive framing

Claims (8 extracted, 0 hedged)

New safeguards sharply reduce AI distillation attacks: Anthropic asserted
safeguards → reduce → attacks
AI generated SAN FRANCISCO – asserted
AI → generate → ?
Anthropic said on Oct 12 that new measures designed to prevent rivals from copying the capabilities of its Claude AI models have reduced data harvested in so-called distillation attacks by about 90% to 99%. asserted
measures → say → 99
Model distillation has emerged as a key concern for leading artificial intelligence companies due to intensifying US-China competition, with firms including Anthropic, OpenAI and Google arguing the practice enables rivals to reproduce advanced capabilities more quickly and at lower cost. asserted
practice → emerge → cost
Anthropic said safeguards restricting access to Claude’s reasoning have sharply reduced extraction attempts, with “the number of reasoning tokens extracted by distillers” now “10 to 100 times lower than it was before”. asserted
it → say → distillers
The California-headquartered company said it had made it harder to use proxy networks to repeatedly probe Claude’s protected reasoning, blocking extraction attempts and hindering large-scale distillation efforts. asserted
it → headquarter → efforts
Anthropic said its safety system is “roughly as robust as those that prevent Claude from helping build bioweapons” and has “a false positive rate of less than 0.1%”. asserted
that → say → %
Anthropic banned tens of thousands of accounts linked to distillation campaigns and cited Chinese AI startup Z.ai, also known as Zhipu, as an example of a company that attempted to distil capabilities from Claude while developing its GLM-5.3 model, warning such practises pose safety and national security risks Z.ai did not immediately respond to a request for comment. asserted
Z.ai → ban → comment
💬Give feedback · no sign-in needed

No sign-in needed for now. Your note is sent without a name, so it cannot be answered.

🕘History 🎫Support
Terms · Privacy · beta v2.0.0
Articles to 5 Nov 2026