Whenever an AI data center thinks really, really hard, it can increase its power consumption so much to trigger disruptions and possibly even blackouts and gear malfunctions. So, is it possible for a malicious actor to trigger this scenario deliberately, in order to cause physical harm?
Multiple researchers from the Zhejiang University in Hangzhou, China, wrote a research paper titled “Bit2Watt: A Cyber-Physical Vulnerability Exploiting GPU Workloads Across Power and Computing Infrastructures.”
In it, they claim that a malicious cloud tenant is, in theory, capable of launching GPU workloads so intensive that they cause physical damage.
Read more…
Source: TechRadar News
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- Link Trap: GenAI Prompt Injection Attack
December 17, 2024
With the rise of generative AI, new security vulnerabilities are emerging. One such vulnerability is prompt injection, a method that malicious actors can exploit to manipulate AI systems. Typically, the impact of prompt injection attacks is closely tied to the permissions granted to the AI. However, the attack discussed in this article differs from commonly known ...
- Proof-of-Concept Released for Critical Apache Struts Vulnerability
December 17, 2024
Apache has released a security bulletin addressing a critical vulnerability in Apache Struts 2. Apache Struts is an open-source model-view-controller (MVC) framework for creating Java web applications. CVE-2024-53677 is a ‘Unrestricted Upload of File with Dangerous Type’ vulnerability and has a CVSSv4 score of 9.5. This vulnerability exists in the File Upload Interceptor, which allows developers ...
- Earth Koshchei Coopts Red Team Tools in Complex RDP Attacks
December 17, 2024
Red teaming provides essential tools and testing methodologies for organizations to strengthen their security defenses. Cybercriminals and advanced persistent threat (APT) actors pay close attention to new methods and tools red teams develop, and they may repurpose them with a malicious intent. In October 2024, an APT group that Trend Micro tracks as Earth Koshchei (also ...
- Task scams surge by 400%, but what are they?
December 16, 2024
An unfamiliar type of scam has surged against everyday people, with a year-over-year increase of some 400%, putting job seekers at risk of losing their time and money. The emerging threat is delivered in “task scams” or “gamified job scams.” While these scams were virtually non-existent in 2020, the FTC reported 5,000 cases in 2023 and ...
- HiatusRAT Actors Targeting Web Cameras and DVRs
December 16, 2024
The Federal Bureau of Investigation (FBI) is releasing this Private Industry Notification (PIN) to highlight HiatusRAT1 scanning campaigns against Chinese-branded web cameras and DVRs. Private sector partners are encouraged to implement the recommendations listed in the “Mitigation” column of the table below to reduce the likelihood and impact of these attack campaigns. Threat HiatusRAT is a ...
- 2024 Threat Landscape Statistics: Ransomware Activity, Vulnerability Exploits, and Attack Trends
December 16, 2024
In this blog, the global experts across our Rapid7 Labs and Managed Services teams share real-time vulnerability insights and threat intelligence so that our customers can anticipate and prevent breaches, pinpoint critical threats, and confidently take command of their attack surface. The Rapid7 Labs team has rounded up statistics and trends that caught their eye throughout ...