Auto Added by WPeMatico
To test the safety and security of AI, hackers have to trick large language models into breaking their own rules. It requires ingenuity and manipulation – and can come at a deep emotional costA few months ago, Valen Tagliabue sat in his hotel room watching his chatbot, and felt euphoric. He had just manipulated it […]
Meet the AI jailbreakers: ‘I see the worst things humanity has produced’ Read More »
Tech can scale cyber-attacks and defences alike, raising questions about private power, public risk and the future of a shared internetAnthropic announced its latest AI model, Claude Mythos, this month but said it would not be released publicly, because it turns computers into crime scenes. The company claimed that it could find previously unknown “zero-day”
Eurail, which sells passes, says data being ‘offered for sale on dark web’ after December breach affecting 300,000 peopleHolidaymakers across Europe are facing the stress and expense of getting new passports after their personal data was posted on the dark web after a hack of the Interrail company Eurail.Personal data, including passport numbers, names, phone
Some Interrail travellers told to cancel passports as hacked data posted online Read More »
Britain’s cybersecurity agency says companies must step up vigilance to prevent espionage attacksBusiness live – latest updatesBritish businesses are being urged to step up their vigilance against a China-linked hacking ploy that uses everyday devices for espionage.The UK’s National Cyber Security Centre (NCSC) and agencies in nine other countries have warned of persistent attempts by
Chinese hackers are using everyday devices to hack UK firms, warns watchdog Read More »
‘Handful’ of people allegedly gain unauthorised access to model adept at detecting cybersecurity vulnerabilitiesBusiness live – latest updatesThe AI developer Anthropic has confirmed it is investigating a report that unauthorised users have gained access to its Mythos model, which it has warned poses risks to cybersecurity.The US startup made the statement after Bloomberg reported on
Anthropic investigates report of rogue access to hack-enabling Mythos AI Read More »
Officials warn a conflict situation could cause disruption similar to recent major ransomware incidentsThe UK could face “hacktivist attacks at scale” if it becomes embroiled in a conflict and the impact could be similar to recent high-profile ransomware incidents, according to the head of the country’s online security agency.Richard Horne, chief executive of the National
UK could face ‘hacktivist attacks at scale’, says head of security agency Read More »
Earlier this month the AI company Anthropic said it had created a model so powerful that, out of a sense of responsibility, it was not going to release it to the public. Anthropic says the model, Mythos Preview, excels at spotting and exploiting vulnerabilities in software, and could pose a severe risk to economies, public
Mythos: are fears over new AI model panic or PR? – podcast Read More »
The group named ShinyHunters have accessed a third party server and have given the company a deadline of 14 April to enter ransom negotiations Rockstar Games, the studio behind Grand Theft Auto, has been the target of a cyberattack for the second time in three years. A hacker group called ShinyHunters said it would release
Hacker group threatens to release Grand Theft Auto VI data in Rockstar Games attack Read More »
US bank has the Claude model and is working closely with the tech firm to improve cyber protectionGoldman Sachs’s chief executive, David Solomon, has said he is “hyper-aware” of the capabilities of Anthropic’s Mythos AI model and is working “closely” with the tech firm after it issued warnings about the cybersecurity risk it poses.The US
Goldman Sachs chief ‘hyper-aware’ of risks from Anthropic’s Mythos AI Read More »
Undisclosed number of names, contact and reservation details are accessed in latest cybercrime attemptBusiness live – latest updatesThe accommodation reservation website Booking.com has suffered a data breach with “unauthorised parties” gaining access to customers’ details.The platform said it “noticed some suspicious activity involving unauthorised third parties being able to access some of our guests’ booking
Booking.com warns customers of hack that exposed their data Read More »
