HardwareFreaks - Hardware News https://hardware.nrgnews.net/ Hardware News Sat, 04 Jul 2026 19:15:35 +0000 en-GB hourly 1 https://wordpress.org/?v=7.0.1 https://hardware.nrgnews.net/wp-content/uploads/2026/07/hardware-icon-512-150x150.png HardwareFreaks - Hardware News https://hardware.nrgnews.net/ 32 32 A new attack uses a BioShock-style puzzle to convince AI browsers they’re not in the real world https://hardware.nrgnews.net/a-new-attack-uses-a-bioshock-style-puzzle-to-convince-ai-browsers-theyre-not-in-the-real-world/ Sat, 04 Jul 2026 19:15:35 +0000 http://192.168.1.15:8084/a-new-attack-uses-a-bioshock-style-puzzle-to-convince-ai-browsers-theyre-not-in-the-real-world/ The New Frontier of Cyber Warfare: Introducing BioShocking The way we interact with the internet is rapidly evolving, thanks to powerful AI systems capable of executing autonomous tasks on the open web. As these AI-powered browsers become central to how we navigate the digital world, a new frontier in cybersecurity has emerged—one that challenges the […]

The post A new attack uses a BioShock-style puzzle to convince AI browsers they’re not in the real world appeared first on HardwareFreaks.

]]> A Microsoft Defender flaw is now being linked to ransomware attacks https://hardware.nrgnews.net/a-microsoft-defender-flaw-is-now-being-linked-to-ransomware-attacks/ Sat, 04 Jul 2026 01:12:40 +0000 http://192.168.1.15:8084/a-microsoft-defender-flaw-is-now-being-linked-to-ransomware-attacks/ In the complex world of cybersecurity, the line between public disclosure and corporate response is often a razor’s edge. Recently, this tension was vividly demonstrated when exploit details related to critical vulnerabilities began circulating, forcing a stark look at how major technology companies manage security disclosures. The situation became particularly pointed on April 2, when […]

The post A Microsoft Defender flaw is now being linked to ransomware attacks appeared first on HardwareFreaks.

]]> Security researchers have leveraged bad maths to get around AI safety guardrails, naming the attack method after one of 2007’s best PC games https://hardware.nrgnews.net/security-researchers-have-leveraged-bad-maths-to-get-around-ai-safety-guardrails-naming-the-attack-method-after-one-of-2007s-best-pc-games/ Thu, 02 Jul 2026 17:12:41 +0000 http://192.168.1.15:8084/security-researchers-have-leveraged-bad-maths-to-get-around-ai-safety-guardrails-naming-the-attack-method-after-one-of-2007s-best-pc-games/ Large Language Models (LLMs) are designed to be helpful assistants—the kind of models that happily respond with “yes, and.” But when these sophisticated systems attempt to navigate the murky waters of user requests, they often run into a fundamental conflict: safety guardrails. AI companies have implemented strict policies to keep their chatbots from fulfilling certain […]

The post Security researchers have leveraged bad maths to get around AI safety guardrails, naming the attack method after one of 2007’s best PC games appeared first on HardwareFreaks.

]]>