Related papers: Non-transferable Pruning
Adaptive network pruning approach has recently drawn significant attention due to its excellent capability to identify the importance and redundancy of layers and filters and customize a suitable pruning solution. However, it remains…
Model stealing attacks have become a serious concern for deep learning models, where an attacker can steal a trained model by querying its black-box API. This can lead to intellectual property theft and other security and privacy risks. The…
Neural network pruning is an essential approach for reducing the computational complexity of deep models so that they can be well deployed on resource-limited devices. Compared with conventional methods, the recently developed dynamic…
In this work, we propose a graph-adaptive pruning (GAP) method for efficient inference of convolutional neural networks (CNNs). In this method, the network is viewed as a computational graph, in which the vertices denote the computation…
The intellectual property protection of deep learning (DL) models has attracted increasing serious concerns. Many works on intellectual property protection for Deep Neural Networks (DNN) models have been proposed. The vast majority of…
Large scale deep learning provides a tremendous opportunity to improve the quality of content recommendation systems by employing both wider and deeper models, but this comes at great infrastructural cost and carbon footprint in modern data…
Pruning neural networks (NNs) can streamline them but risks removing vital parameters from safe reinforcement learning (RL) policies. We introduce an interpretable RL method called VERINTER, which combines NN pruning with model checking to…
Structural design of neural networks is crucial for the success of deep learning. While most prior works in evolutionary learning aim at directly searching the structure of a network, few attempts have been made on another promising track,…
Deep neural networks (DNNs), trained with gradient-based optimization and backpropagation, are currently the primary tool in modern artificial intelligence, machine learning, and data science. In many applications, DNNs are trained offline,…
The great economic values of deep neural networks (DNNs) urge AI enterprises to protect their intellectual property (IP) for these models. Recently, proof-of-training (PoT) has been proposed as a promising solution to DNN IP protection,…
A major challenge in applying differential privacy to training deep neural network models is scalability.The widely-used training algorithm, differentially private stochastic gradient descent (DP-SGD), struggles with training…
As spiking neural networks (SNNs) gain traction in deploying neuromorphic computing solutions, protecting their intellectual property (IP) has become crucial. Without adequate safeguards, proprietary SNN architectures are at risk of theft,…
The remarkable performance of modern deep neural networks (DNNs) is largely driven by their massive scale, often comprising tens to hundreds of millions-or even billions-of parameters. However, such a scale incurs substantial storage and…
We present a systematic weight pruning framework of deep neural networks (DNNs) using the alternating direction method of multipliers (ADMM). We first formulate the weight pruning problem of DNNs as a constrained nonconvex optimization…
To explore the vulnerability of deep neural networks (DNNs), many attack paradigms have been well studied, such as the poisoning-based backdoor attack in the training stage and the adversarial attack in the inference stage. In this paper,…
Model pruning has gained traction as a promising defense strategy against backdoor attacks in deep learning. However, existing pruning-based approaches often fall short in accurately identifying and removing the specific parameters…
Foundation models and their checkpoints have significantly advanced deep learning, boosting performance across various applications. However, fine-tuned models often struggle outside their specific domains and exhibit considerable…
Integrated photonic neural networks (PNNs) are at the forefront of AI computing, leveraging on light's unique properties, such as large bandwidth, low latency, and potentially low power consumption. Nevertheless, the integrated optical…
Model compression is an essential technique for deploying deep neural networks (DNNs) on power and memory-constrained resources. However, existing model-compression methods often rely on human expertise and focus on parameters' local…
Malware allegedly developed by nation-states, also known as advanced persistent threats (APT), are becoming more common. The task of attributing an APT to a specific nation-state or classifying it to the correct APT family is challenging…