Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defense. (arXiv:2304.06919v1 [cs.LG])

While having achieved great success in rich real-life applications, deep
neural network (DNN) models have long been criticized for their vulnerability
to adversarial attacks. Tremendous research efforts have been dedicated to
mitigating the threats of adversarial attacks, but the essential trait of
adversarial examples is not yet clear, and most existing methods are yet
vulnerable to hybrid attacks and suffer from counterattacks. In light of this,
in this paper, we first reveal a gradient-based correlation between sensitivity
analysis-based DNN interpreters …

adversarial adversarial attacks adversary analysis applications attacks correlation counterattacks defense great hybrid life network neural network process research safety threats vulnerability vulnerable