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:
- More xHunt – New PowerShell Backdoor Blocked Through DNS Tunnel Detection
October 10, 2019
During our continued analysis of the xHunt campaign, we observed several domains with ties to the pasta58com, being used as the C2 server for a new PowerShell based backdoor that we’ve named CASHY200. This PowerShell backdoor ...
- CVE-2019-16928: Exploiting an Exim Vulnerability via EHLO Strings
October 10, 2019
In September, security researchers from the QAX-A-Team discovered the existence of CVE-2019-16928, a vulnerability involving the mail transfer agent Exim. Exim accounts for over 50% of publicly reachable mail servers on the internet. What makes the bug particularly noteworthy is that threat actors could exploit it to perform denial of service (DoS) or possibly even remote code execution ...
- Intelligence Agencies Warn Of Flaw With VPN Products
October 9, 2019
Both the US NSA and UK NCSC warn hackers are actively exploiting vulnerabilities in VPN products Both the US National Security Agency (NSA) and a GQHC agency in the United Kingdom have issued warnings about “multiple vulnerabilities in Virtual Private Network (VPN) applications.” Both the NSA and the UK’s National Cyber Security Centre (NCSC) warned that advanced persistent threat (APT) ...
- FIN6 Compromised E-commerce Platform via Magecart to Inject Credit Card Skimmers Into Thousands of Online Shops
October 9, 2019
trend Micro discovered that the online credit card skimming attack known as Magecart or E-Skimming was actively operating on 3,126 online shops. Our data shows that the attack started on September 7, 2019. All of the impacted online shops are hosted on the cloud platform of the e-commerce service provider “Volusion,” one of the top e-commerce platforms in the market. ...
- The Value of Dark Web Coverage for Third-Party Risk Management
October 9, 2019
Everyone knows that a key ingredient to an effective third-party risk program is comprehensive, high-quality risk information. This includes details on supply chain risk, financial risk, legal risk, cyber risk, and more. With growing third-party ecosystems, it’s easier said than done for risk management teams to collect, organize, and prioritize their own risk information along ...
- Report: Nation state hackers and cyber criminals are spoofing each other
October 4, 2019
Nation-state hackers and cyber criminals are increasingly impersonating each other to try and hide their tracks as part of advanced attack techniques says Optiv Security in its 2019 Cyber Threat Intelligence Estimate report. The top industries being targeted are retail, healthcare, government and financial institutions. Cryptojacking and ransomware are new exploits that join the traditional list of computer ...