In addition to evoking the horcruxes that kept pieces of Lord Voldemort\u2019s soul alive within objects in the Harry Potter series, the report alarmed some professionals because the generally weak security of smart televisions and many other \u201cinternet of things\u201d devices would be very hard to correct, even with a concerted effort.<\/p>\n
\u201cIt\u2019s something to worry about just like every other wave of cyber-attacks. We need to mitigate the possible effects,\u201d said Joshua Saxe, who led development of Meta\u2019s AI security effort. \u201cI\u2019m concerned right now that folks in the cybersecurity community are not taking these kinds of real risks as seriously as they should be.\u201d<\/p>\n
The damage of such \u201cAI worms\u201d could be astonishingly large. Self-replicating computer viruses, which need not trick a human to propagate, are known as worms, and earlier worms have wreaked some of the worst havoc in the history of the internet.<\/p>\n
That legacy includes the Morris worm of 1988, which arrived before the mainstream consumer internet, when a graduate student released a program that took advantage of various software flaws and weak passwords, copying itself so rapidly that many infected machines slowed to a stop. The US and Israel brought worms into international espionage with the stealthy Stuxnet in the lat 2000s, which sabotaged Iranian nuclear centrifuges. Other worms like the Russian NotPetya<\/a> and North Korean-attributed WannaCry have caused tens of billions of dollars\u2019 worth of damage worldwide.<\/p>\n Many of the world\u2019s most destructive worms have depended on known vulnerabilities that device owners have not patched, sometimes months after patches became available. The Anthropic<\/a> team predicted that a worm like theirs could function in the same way and be harder to stop, because smart devices receive patches less often than phones or laptops. Worse, they theorized that an AI worm could keep adapting to other types of hardware by researching newly disclosed vulnerabilities.<\/p>\n What differentiates AI worms from typical reproducing viruses is that AI models can learn as they go, said Ariel Herbert-Voss, an early security expert at OpenAI who now runs AI security startup RunSybil. Existing cybersecurity infrastructure is not ready for the proliferation of such threats, Herbert-Voss said. \u201cWe need to better enable our security teams. We need to be giving them more resources to fix problems.\u201d<\/p>\n Worms could also be used for benevolent purposes, suggested Chris Inglis, a former deputy director of the National Security Agency who served as National Cyber Director in the Biden White House.<\/p>\n \u201cThe question of whether AI worms are plausible has been settled by several breakout events over the past six months,\u201d Inglis said by digital message. \u201cThe better question is how we will employ them, counter them, and\/or combine them with other emerging technologies.\u201d<\/p>\n Anthropic researchers said a successful AI worm would need to have more capability on less powerful devices than is possible right now \u2013 but they added that current trends will make that feasible by year\u2019s end. Their research follows a paper<\/a> published by experts at the University of Toronto a few months ago, which infected a full-size computer and could spread to similar machines more rapidly than the television worm.<\/p>\n \u201cThe capabilities have been developing very rapidly,\u201d said co-author and Toronto PhD student Jonas Guan.<\/p>\n
![\"\"](\"https:\/\/www.newsbeep.com\/au\/wp-content\/uploads\/2026\/10\/1792406671_487_500.jpg\")
<\/p>\n