The architecture information of a Deep Neural Network (DNN) model is considered a valuable, sensitive piece of property for a company. Knowledge of a DNN’s exact architecture allows any adversary to build a substitute model and use this substitute model to launch devastating adversarial attacks. Side-channel based DNN architecture stealing can...

­One practical limitation of deep neural network (DNN) is its high degree of specialization to a single task or domain (e.g., one visual domain). This motivates the development of algorithms that can adapt DNN model to multiple domains sequentially while still performing well on past domains. This is known as multi-domain learning. Conventional...

­Recently, Deep Neural Networks (DNNs) have been deployed in many safety-critical applications. The security of DNN models can be compromised by adversarial input examples, where the adversary maliciously crafts and adds input noise to fool a DNN model. The perturbation of model parameters (e.g., weight) is another security concern, one that relates...