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 2026-11-21, grounded in this article and the 0 other(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.
The Straits Times
Leans left Hedges 5 of 18 claims Outlet record 64/100
“The articles describe different policies by Anthropic: one about banning cruel behavior against Claude AI, and another about reducing distillation attacks.”
CBS News
Hedges 1 of 2 claims Outlet record 66/100
“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.”

Story

AI Security Improvements
Technology · 1 article(s) covering the same event.
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
64/100
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 · 5679 article(s) · 7 correction(s) detected
Running correction rate · 7 correction(s)

Who wrote this

The Straits Times
3972 article(s) here · 0 carrying a prediction
• The former president is clinically stable and conscious but there is no forecasted discharge at this time
2026-11-21 · assertive framing · Brazil ex-President Jair Bolsonaro taken to ICU
The environmental consequences of this war will last for generations,” Lewis Pugh wrote in a post on his website.
He predicts that pairing more use of these Wolbachia mosquitoes with existing steps to fight mosquito-borne disease could “knock dengue down to much lower levels” in many places.
Gharibabadi echoed remarks by Iranian Foreign Minister Abbas Araqchi in an interview with the state-owned Iran newspaper that Tehran still hoped diplomacy could end its war with the United States.
The Estonian police said on Nov 20 the closure would “make it harder for Russian intelligence services to recruit and influence people, and help prevent sanctions evasion”.
2026-11-21 · assertive framing · Queues in Russian town as Estonia border closure looms
COP31 climate summit risks failure as talks go deep into overtime ANTALYA, Turkey, Nov 21 - The COP31 climate summit will either produce a good deal or no deal at all, the European Union's top climate official said on Saturday as talks stretched deep into overtime.
He was considered one of the leaders of the Beltran Leyva cartel, which had reportedly allied with the Los Mayors faction of the powerful Sinaloa Cartel.
Trump told European leaders they were spending a lot on Ukraine, Zelenskiy says KYIV, Nov 21 - US President Donald Trump told European leaders this week they were spending a lot on the war in Ukraine and could use that money at home if a peace deal were reached with Russia, Ukrainian President Volodymyr Zelenskiy said on Saturday.
Denmark would present its proposals at a meeting of EU ambassadors in Brussels on Monday.
NATO will defend every inch of Polish territory, Rutte says WARSAW, Nov 21 - NATO will defend every inch of Polish territory, NATO Secretary General Mark Rutte said in Warsaw, a day after Poland said Russia violated its airspace with three objects that were probably two missiles and a drone.
Also by The Straits Times
Brazil ex-President Jair Bolsonaro taken to ICU
2026-11-21 · The Straits Times
Nothing else under this byline is closely related to this article, so these are simply their most recent.
All 3972 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