Breaking things is easy

Until a few years ago, machine learning algorithms simply did not work very well on many meaningful tasks like recognizing objects or translation. Thus, when a machine learning algorithm failed to do the right thing, this was the exception, rather than the rule. Today, machine learning algorithms have advanced to the next stage of development: when presented with naturally occurring inputs, they can outperform humans. Machine learning has not yet reached true human-level performance, because when confronted by even a trivial adversary, most machine learning algorithms fail dramatically. In other words, we have reached the point where machine learning works, but may easily be broken. This blog post serves to introduce our new Clever Hans blog, in which we will discuss all of the many ways an attacker can break a machine learning algorithm.