7th Intl. Conference on Big Data, Cybersecurity & Artificial Intelligence Held in the spectacular main Lecture theatre on Edinburgh Napier University’s Craiglockhart Campus. The photo is of Professor Bill Buchanan’s opening keynote talk about AI and us. In between looking at how ChatGPT words can be found in university submitted …
How to deceive an LLM AI
Bruse Schneier has an excellent article on how large language model AIs are being maliciously manipulated because of an old-style vulnerability being exploited. AT&T was probably the first organisation hit by such an attack that exploits systems that use the same channel for both data and commands. Back in the …
Includes “AI” for your convenience!
I have lost track of the number of services that I am being offered include “AI” to make them better, more helpful, intuitive, etc., etc., etc.. Even my Microsoft 365 for Business comes with AI interfering, sorry helping at every turn. But what happens when the threat actors get their …
See what Bruce Schneier has to say about Microsoft spying on you!
Most days I read what Bruce Schneier has to say, I have also seen him speak and bought (and quoted from) his books. This piece is short and to the point: Microsoft Is Spying on Users of Its AI Tools – Schneier on Security Your takeaway Sometimes you just have …
Continue reading “See what Bruce Schneier has to say about Microsoft spying on you!”
AI and your Cyber Security
This article by Oli Buckley, Professor of Cyber Security at the University of East Anglia and Jason Nurse, Associate Professor in Cyber Security at the University of Kent takes a balanced look at how AI is starting to help threat actors create more believable attacks. Cybercriminals are creating their own …
Updates and Patches
The US government Cybersecurity and Infrastructure Security Agency (CISA) is one of our go-to information sources for cyber security information. Whilst I have been away my team have been keeping up with the news there, but I have not! Here is a round-up of their latest alerts: VMware Releases Security …
Towards Secure AI
The UK’s National Cyber Security Centre has joined with other international government agencies, with responsibility for cyber security, from around the world to create guidelines for the secure developement of AI systems. These guideline cover, data poisoning, input manipulation, privacy and IP threats, re-identification of anonomised data, model stealing and …