BSI AI Guideline

ByStefan Karg

What a good start into the weekend 😎

📄 The German BSI has published a guideline for developers regarding potential vulnerabilies in AI systems.

📣 From my point of view, a security risk assessment on systems using AI technologies has to consider the attacks on the AI parts of the system as well. A security risk assessment only considering the IT security aspects of such systems but neglecting the AI security of the system cannot be considered as complete any more.

You can find the pdf at this link when searching for “AI security concerns in a nutshell – Practical AI-Security guide”.

Similar Posts

  • WormGPT and FraudGPT

    ByStefan Karg

    As with any new technology, the “other side” is trying to figure out how to use it to their advantage. The normal commercial versions of LLMs have barriers built in to prevent the creation of malware code or phishing mails, for example. If you remove these barriers, you get the output that we as security…

  • AI phishing

    ByStefan Karg

    Are the bad guys using AI? They might! AI tools like ChatGPT or DALL-E-2 are currently widely tested out on the internet – both for the good as well as for the bad. From my point of view, we are at the very beginning of an interesting development, which will unfold over the next couple…

  • AI tracking

    ByStefan Karg

    AI can track the time you spend on your phone during work. The post below shows an interesting demonstration of the technical capabilities. From my point of view, these kind of AI applications will be and should be a focus of a broad public discussion in the near future. AI applications will offer great opportunities,…