Some find it fascinating, others are directly involved in its further development, and third, it gives a queasy feeling in the stomach: We are talking about artificial intelligence, or AI for short. Although the technology is already being used in many places and has unbelievably great potential, it does not only generate enthusiasm. AI security, in particular, is perceived as a problem by many people – laypeople and experts alike. We clarify and dedicate ourselves to the following five central facts about AI security.
1: Survey Reveals Seven Main Problems For AIs And AI Safety
First of all, it’s worth taking a look at a survey that came out of a collaboration between BlackBerry Cylance and the SANS Institute in 2018. The survey interviewed a total of 260 cybersecurity experts who ultimately identified seven major problems with the technology:
- Unreasonable reliance on a single AI master algorithm
- Negative impact on privacy
- Lack of understanding of the limits of an algorithm
- Inappropriate training situations
- Insufficiently protected data and metadata
- Lack of transparency regarding the algorithms decision-making methods
- Incorrectly used algorithms
2: A Study By The BSI And ANSSI On AI Security Comes To a Questionable Result
A study carried out by the BSI (Federal Office for Information Security) and the French ANSSI (Agence nationale de la sécurité des systèmes d’information) is also interesting.
The result: The database of neural networks and the data input are highly vulnerable, and there are reliability problems that could have potentially dangerous consequences. The fallibility of artificial intelligence should not be underestimated and should be recognized as a real danger, especially about the use of AI in critical task areas such as autonomous driving or medical diagnosis.
3: “Data poisoning” Is Seen As a Major Threat To AI Security
The term “data poisoning” is becoming more and more popular – but what exactly does it mean? Put simply, it is the intentional feeding of the machine learning system with incorrect data, which falsifies the entire environment. Hence, a clear threat to AI security and the reliability of supposedly “safe”, self-learning AI applications.
4: Experts Rate GAN Trend As Dangerous
Another topic that must not be concealed with regard to AI security relates to Generative Adversarial Networks, GAN for short. Translated into German, this trend stands for “generating, opposing networks”. Two neural networks work as opponents here: training data are used, from which one network creates a candidate, which is then accepted or rejected by the second network – the so-called discriminator. Many experts view this technology as dangerous because it has the potential to make harmful instruments or even weapons out of neural networks.
5: Trust In AI Security Needs To Be Regained
If you look through the population, you can see that trust in AIs and AI security has been almost completely lost in many places. The origin of the mistrust is based on the one hand in a lack of knowledge, on the other hand on extensive knowledge regarding the potential dangers of artificial intelligence. If the future is to bring a significant increase in AI applications in a business context, but also in everyday private life, a lot of educational work must be done, on AI security and the problems.