Prompt injection attacks threaten AI chatbots and other news – The News Intel>
– Posted by admin
UK cybersecurity agency warns against attacks targetting AI chatbots The UK’s National Cyber Security Centre (NCSC) has highlighted a growing risk of chatbots being manipulated by hackers [through “prompt injection” attacks](https://www.ncsc.gov.uk/blog-post/thinking-about-security-ai-systems).To accelerate public-private responses to address the global cybersecurity skills and talent gap, the [World Economic Forum Centre for Cybersecurity](https://www.weforum.org/platforms/the-centre-for-cybersecurity) has launched the “Bridging the Cyber Skills Gap” initiative.Among other things, the initiative seeks to: Raise awareness and share knowledge amongst C-suite executives and decision-makers about cybersecurity skills deficit and its economic and security implicationsDefine strategic approaches and processes that will help build sustainable cyber talent pipelines within organizations and across sectors and geographies The Forum has also partnered with [Salesforce](https://www.weforum.org/organizations/salesforce), [Fortinet](https://www.weforum.org/organizations/fortinet) and the [Global Cyber Alliance](https://www.globalcyberalliance.org/) to delivering free and globally accessible cybersecurity training through the [Cybersecurity Learning Hub](https://trailhead.salesforce.com/cybersecurity/).World Economic Forum partner Absa, in collaboration with the Maharishi Institute, have also developed the [Absa Cybersecurity Academy](https://www.absa.africa/a-force-for-good/cybersecurity-academy/academy/) that is targeting some of the most disadvantaged groups in South Africa.Data breaches continue to soar in 2023 The number of data breaches worldwide saw a 156% increase [between Q1 and Q2 2023](https://surfshark.com/research/study/data-breach-statistics-q2-2023), according to new figures from VPN provider Surfshark.News in brief: Top cybersecurity stories this month Japan’s [national cyber defence agency has been infiltrated by hackers](https://www.ft.com/content/de0042f8-a7ce-4db5-bf7b-aed8ad3a4cfd), who may have had access to information for as much as nine months, the Financial Times reports.The Five Eyes intelligence alliance has detailed how Russian state-sponsored hackers Sandworm are using an [Android malware called Infamous Chisel](https://www.cisa.gov/news-events/alerts/2023/08/31/cisa-and-international-partners-release-malware-analysis-report-infamous-chisel-mobile-malware) to attack Ukranian soldiers’ devices, scan files, monitor traffic and steal sensitive information.More on cybersecurity on Agenda The World Economic Forum’s Global Coalition for Digital Safety has produced a [foundational language to define online harms](https://www.weforum.org/agenda/2023/09/definitions-online-harm-internet-safer/).[Technology’s impact on productivity growth has been consistently overstated](https://www.weforum.org/agenda/2023/08/generative-ai-realistic-economic-impact/), they say, and analysts could be repeating that mistake with generative AI.
Link: https://thenewsintel.com/prompt-injection-attacks-threaten-ai-chatbots-and-other-news/