The world is changing in front of our eyes. Where facts, truth and honesty were once our most valuable assets, nowadays alternative-facts, post-truths and outright lies reign. Unfortunately, the cybersecurity business is no exception to this trend.
Even worse, with all the recent advances in the field of artificial intelligence (AI) and machine learning (ML), cybersecurity is all the more complicated and confusing – opening opportunities for some players who like to inflate their abilities and ignore the limitations.
Machine learning algorithms as a cybersecurity silver bullet? No need for updates, or the downplayed importance of false positives; those are just a few of the often used marketing tricks from the toolbox of these “next-gen” – or as we call them – “post-truth” vendors.
These false claims, however, go against the fact-based experience of established vendors such as ESET, which has fought the cybersecurity fight for almost three decades and know the possible downsides.
To bring more clarity to the murky waters of post-truth marketing, we at WeLiveSecurity have decided to release a series of short articles focused on the currents state of AI, all the ins and outs of ML, and ML as it affects cybersecurity.
Committed to the values of truth and honesty, we will explain how machine learning in cybersecurity works, what the limits of this recently rediscovered technology are in real-world environments and why it is still not mature enough to be the only layer standing between you and cyberattackers.
Just to give you an overview of what you can read over the next few weeks:
- Editorial: Fighting post-truth with reality in cybersecurity
- What is machine learning and artificial intelligence?
- Most frequent misconceptions about ML and AI
- Why ML-based security doesn’t scare intelligent adversaries
- Why one line of cyberdefense is not enough, even if it’s machine learning
- Chasing ghosts: The real costs of high false positive rates in cybersecurity
- How updates make your security solution stronger
- We know ML, we’ve been using it for over a decade
We hope you’ll enjoy it.
With contribution of Jakub Debski & Peter Kosinar