This paper was selected for Top Picks in Hardware and Embedded Security 2020 and it presents a physical side-channel attack aiming at reverse engineering neural networks implemented on an edge device. The attack does not need access to training data and allows for neural network recovery by feeding known random inputs. We successfully reverse engineer information about layers, neurons, activation functions, and weights associated with neurons. This attack opens a new door in the domain of security of neural networks. Follow-up works by other researchers have shown this attack to be applicable for various settings and difficult to protect against.@en

Machine learning has become mainstream across industries. Numerous examples prove the validity of it for security applications. In this work, we investigate how to reverse engineer a neural network by using side-channel information such as timing and electromagnetic (EM) emanations. To this end, we consider multilayer perceptron and convolutional neural networks as the machine learning architectures of choice and assume a non-invasive and passive attacker capable of measuring those kinds of leakages. We conduct all experiments on real data and commonly used neural network architectures in order to properly assess the applicability and extendability of those attacks. Practical results are shown on an ARM Cortex-M3 microcontroller, which is a platform often used in pervasive applications using neural networks such as wearables, surveillance cameras, etc. Our experiments show that a side-channel attacker is capable of obtaining the following information: the activation functions used in the architecture, the number of layers and neurons in the layers, the number of output classes, and weights in the neural network. Thus, the attacker can effectively reverse engineer the network using merely side-channel information such as timing or EM.@en

The use of deep learning-based side-channel analysis is an effective way of performing profiling attacks on power and electromagnetic leakages, even against targets protected with countermeasures. While many research articles have reported successful results, they typically focus on profiling and attacking a single device, assuming that leakages are similar between devices of the same type. However, this assumption is not always realistic due to variations in hardware and measurement setups, creating what is known as the portability problem. Profiling multiple devices has been proposed as a solution, but obtaining access to these devices may pose a challenge for attackers. This article proposes a new approach to overcome the portability problem by introducing a neural network layer assessment methodology based on the ablation paradigm. This methodology evaluates the sensitivity and resilience of each layer, providing valuable knowledge to create a Multiple Device Model from Single Device (MDMSD). Specifically, it involves ablating a specific neural network section and performing recovery training. As a result, the profiling model, trained initially on a single device, can be generalized to leakage traces measured from various devices. By addressing the portability problem through a single device, practical side-channel attacks could be more accessible and effective for attackers.@en

The use of deep learning-based side-channel analysis is an effective way of performing profiling attacks on power and electromagnetic leakages, even against targets protected with countermeasures. While many research articles have reported successful results, they typically focus on profiling and attacking a single device, assuming that leakages are similar between devices of the same type. However, this assumption is not always realistic due to variations in hardware and measurement setups, creating what is known as the portability problem. Profiling multiple devices has been proposed as a solution, but obtaining access to these devices may pose a challenge for attackers. This article proposes a new approach to overcome the portability problem by introducing a neural network layer assessment methodology based on the ablation paradigm. This methodology evaluates the sensitivity and resilience of each layer, providing valuable knowledge to create a Multiple Device Model from Single Device (MDMSD). Specifically, it involves ablating a specific neural network section and performing recovery training. As a result, the profiling model, trained initially on a single device, can be generalized to leakage traces measured from various devices. By addressing the portability problem through a single device, practical side-channel attacks could be more accessible and effective for attackers.@en