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 2026-11-20, 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 67/100
“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 · 5594 article(s) · 7 correction(s) detected
Running correction rate · 7 correction(s)

Who wrote this

The Straits Times
3846 article(s) here · 0 carrying a prediction
BERLIN, Nov 20 - German Defence Minister Boris Pistorius said on Friday he had apologised for calling Pentagon policy chief Elbridge Colby's opposition to Ukrainian deep strikes into Russia "stupid" but that he would not withdraw his criticism. Tuesday's testy exchange at the NATO alliance's Brussels headquarters exposed a rift between Washington and Europe over Ukraine's military strategy of trying to take the fight inside Russia in the nearly five-year-old war since Moscow's invasion. "In hindsight, I actually think the choice of words was inappropriate – and I didn't really think it was appropriate even shortly after," Pistorius told the Politico news outlet, saying he had used an unfortunate turn of phrase as a non-native speaker in a news conference. "I shouldn't have done that," he noted, adding he had called Colby on Wednesday to discuss the incident.
While not game-changing in themselves, this week’s attacks pile pressure on an already strained logistics network in ways that Russia could struggle to mitigate, two analysts and two Ukrainian commanders said. Hitting the showcase Russian project had a strong symbolic impact, particularly in the build-up to President Vladimir Putin’s unprecedented three-way meeting with US President Donald Trump and Chinese President Xi Jinping on Nov 19.
Climate summits often end with a final text, meant to address how the world will deal with climate change.
Three bridges that cross the Dnipro river were also hit, Mayor Vitali Klitschko said, threatening yet more disruption to daily life in the city.
"Russia will have to answer for this," Jean-Noel Barrot wrote in a post on social media platform X.
Russia accuses Estonia of erecting new 'Iron Curtain' with border closure, says it will respond MOSCOW, Nov 20 - Russian Foreign Ministry spokeswoman Maria Zakharova on Friday accused Estonia of planning to erect a new "Iron Curtain" and said it would respond after Estonia said it would close its border with Russia for at least six months.
The outbreak’s location in a part of eastern Congo already facing a humanitarian crisis could be complicating what scientists are finding, several experts said, and cautioned against drawing early conclusions as data is limited, varied and often difficult to collect.
Two men to stand trial in UK next year over RAF Fairford incident allegedly linked to Iran LONDON, Nov 20 - Two men charged over September's security incident at the RAF Fairford military base, which British and US prosecutors say was orchestrated on behalf of Iran, will stand trial in London in November next year, a judge said on Friday.
VILNIUS – Estonia will close its border crossings with Russia for at least six months from Dec 1 on security grounds, the Baltic country’s government said on Nov 20.
"WE WILL TAKE OUR FUTURE BACK"
Also by The Straits Times
Nothing else under this byline is closely related to this article, so these are simply their most recent.
All 3846 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