Characterizing the Weight Space for Different Learning Models
This work addresses adversarial vulnerability in deep learning systems, which is an incremental improvement for enhancing AI safety and security.
The paper characterizes the weight space of deep neural networks into exact, generalized, and adversarial subsets, and compares it with associative memory models, showing that adversarial attacks are less successful against associative memory models.
Deep Learning has become one of the primary research areas in developing intelligent machines. Most of the well-known applications (such as Speech Recognition, Image Processing and NLP) of AI are driven by Deep Learning. Deep Learning algorithms mimic human brain using artificial neural networks and progressively learn to accurately solve a given problem. But there are significant challenges in Deep Learning systems. There have been many attempts to make deep learning models imitate the biological neural network. However, many deep learning models have performed poorly in the presence of adversarial examples. Poor performance in adversarial examples leads to adversarial attacks and in turn leads to safety and security in most of the applications. In this paper we make an attempt to characterize the solution space of a deep neural network in terms of three different subsets viz. weights belonging to exact trained patterns, weights belonging to generalized pattern set and weights belonging to adversarial pattern sets. We attempt to characterize the solution space with two seemingly different learning paradigms viz. the Deep Neural Networks and the Dense Associative Memory Model, which try to achieve learning via quite different mechanisms. We also show that adversarial attacks are generally less successful against Associative Memory Models than Deep Neural Networks.