Attack Strength vs. Detectability Dilemma in Adversarial Machine Learning

By Christopher Frederickson, Michael Moore, Glenn Dawson, Robi Polikar. 2018

36 citations recorded by the source corpus.

As the prevalence and everyday use of machine learning algorithms, along with our reliance on these algorithms grow dramatically, so do the efforts to attack and undermine these algorithms with malicious intent, resulting in a growing interest in adversarial machine learning. A number of approaches have been developed that can render a machine learning algorithm ineffective through poisoning or other types of attacks. Most attack algorithms typically use sophisticated optimization approaches, whose objective function is designed to cause maximum damage to accuracy or performance of the algorithm with respect to some task. In this effort, we show that while such an objective function is indeed brutally effective in causing maximum damage on an embedded feature selection task, it often results in an attack mechanism that can be easily detected with an embarrassingly simple novelty or outlier detection algorithm. We then propose an equally simple yet elegant solution by adding a regularization term to the attacker's objective function that penalizes outlying attack points.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Stronger data poisoning attacks break data sanitization defenses (2018, background): “, 2017), whereas attacks that are not optimized can be easily detected as anomalies (Frederickson et al., 2018).”