Anthropic blocks 'malicious use' of AI that could develop biological weapons
The revelations in Anthropic's threat intelligence report come after a former top researcher at the company warned of the risks of AI to humanity.
Anthropic says it has stopped attempts to use its AI for “malicious activity” that could aid the development of biological and conventional weapons.
According to the company’s latest threat intelligence report, its Claude model was also used in a Russia-linked cyber espionage campaign and by an Iranian propaganda institution.
Over the past eight months, the cases flagged by Anthropic ranged from fake dating apps and hotel Wifi scams to surveillance systems designed to identify dissidents.
The disclosures follow warnings from a senior Anthropic safety researcher about the potential risks AI poses to humanity.
Anthropic has also accused Chinese AI companies of attempting to copy Claude’s capabilities.
The company released its latest threat intelligence report, external, on Thursday, saying it did so because it believes it has “a responsibility to disclose malicious misuse of our services”.
The extensive report details cases in which suspected state-sponsored groups, criminals, spyware vendors, state propaganda institutions and politically motivated individuals misused its technology.
It said “malicious use” of its Claude Haiku, Sonnet, and Opus models was disrupted between December 2025 and August 2026.
None of the misuse cases involved Claude Fable or the powerful Mythos-class models, except for one case of distillation - the process of training smaller AI models using larger, more expensive models.
In addition to identifying the use of its models in cyber and influence operations, surveillance, scams and fraud, and weapon development, Anthropic said it had blocked scientists who used its AI in ways that could support biological weapons development.
The report highlighted “five case studies of actors using our models in ways that could support biological weapons development”.
It said biological misuse is “one of the most serious risks of frontier AI model”. Without the right safeguards, such capabilities “could have catastrophic consequences”, Anthropic said.
“The same information that can be used to develop a biological weapon could also be used to develop, for example, a vaccine or a cure for a disease,” Anthropic said.
Jacob Klein, Anthropic’s head of threat intelligence, told the
“You are not seeing someone in a comic book kind of way say, ‘Hey, I want to build a biological weapon to kill everybody,’” he said.
The report also identified six cases in which Claude was used “to develop software for conventional weapons, including firearms, missiles, armed drones, bombs, and other munitions, as well as the targeting and control systems that operate them”.
It said cybercriminals and state-backed hackers have increasingly used its technology to support their operations.
Hacking group ShinyHunters, along with China-based labs, were among those named in the report.
The report also said a hacking group whose activity is consistent with the Russia-based Midnight Blizzard allegedly used AI to build a system that automatically detected when its malware was flagged by security defences and rewrote code until it evaded detection.
The California-based company said it had fed its findings into its processes “to better prevent, detect, and disrupt these activities in the future”.
Anthropic said it had shared intelligence with authorities and industry partners where appropriate.
The report - the company’s first this year - comes after a top Anthropic safety researcher warned that AI is advancing so quickly he believes there is a greater than 10% chance it “could kill all humans” within the next decade.
In an articled published on 6 September, OpenAI chief scientist Jakub Pachocki called for the industry to adopt “voluntary slowdowns” until safeguards are in place.
“I am concerned no one is prepared for the consequences of a continued rapid rise in machine intelligence,” Pachocki said, adding that OpenAI, which makes ChatGPT, will continue working on safeguards, though broader interventions are needed.
The warning led to an open letter to UK Prime Minister Andy Burnham calling for a new multinational treaty for the safe development of AI, and a call for governments to work together on what a treaty based on the development of superintelligence should look like.
In the US, Democratic lawmaker Bernie Sanders has introduced legislation to ban AI superintelligence and temporarily pause advanced AI development.
“When scientists tell you there is a chance, a chance that it could have a cataclysmic impact on humanity, you’ve got be a moron not to say, slow it down,” he said on Thursday on