Tracked topic
Cybersecurity covers information-security practice — vulnerabilities, breaches, malware, and defensive security operations; related to but distinct from privacy.
…According to cybersecurity firm Socket, which focuses on software supply chains, TeamPCP has, in just the last few months, carried out 20 “waves” of supply chain attacks that have hidden malware in…
…Independent cybersecurity experts have increasingly taken the view that guardrails on AI models are only a stopgap, since skilled users and future AI models will find ways to bypass constraints. A White…
…Though bugs and cybersecurity problems get a lot of attention—especially of late—Ghosh tells me that problems with AI systems span topics like psychological harm, discrimination or bias, and misinformation. He…
…the White House early access to AI models ahead of their public release to evaluate cybersecurity capabilities. At its core, the push for regulation reflects a recognition inside the White House that…
…The company said it would reroute users who asked questions about cybersecurity, biology, or chemistry to a less capable AI model to reduce the chances of someone using the advanced AI to…
…The Amazon researchers claimed that it was possible to circumvent some of Fable 5’s guardrails and access Mythos’ formidable cybercapabilities, though Anthropic and outside cybersecurity experts have argued these risks are…
…Nevertheless, through reporting by 404 Media and analysis from experts such as cybersecurity specialist Andrea Fortuna, we can make some educated guesses about what happened. What seems clear is that the forensics…
…But as AI labs continue to release more powerful AI models that raise novel safety and cybersecurity challenges, such as Anthropic’s Claude Mythos, these questions feel increasingly prescient. In her testimony…
…The situation feels particularly urgent in the wake of Anthropic’s latest model, known as Mythos, which has been called a “cybersecurity reckoning,” due to its advanced ability to find zero-day…
…Anthropic and independent cybersecurity researchers argue that solving jailbreaks is not an easy or isolated issue. Because AI models are probabilistic, not deterministic, tech companies can’t guarantee what exactly they will…