相关论文: DivQAT: Enhancing Robustness of Quantized Convolut…

Neural networks are valuable intellectual property due to the significant computational cost, expert labor, and proprietary data involved in their development. Consequently, protecting their parameters is critical not only for maintaining a…

Deep neural networks (DNNs) have demonstrated their great potential in recent years, exceeding the per-formance of human experts in a wide range of applications. Due to their large sizes, however, compressiontechniques such as weight…

Neural network quantization methods often involve simulating the quantization process during training, making the trained model highly dependent on the target bit-width and precise way quantization is performed. Robust quantization offers…

Quantization is a popular technique that $transforms$ the parameter representation of a neural network from floating-point numbers into lower-precision ones ($e.g.$, 8-bit integers). It reduces the memory footprint and the computational…

Network quantization is an effective method for the deployment of neural networks on memory and energy constrained mobile devices. In this paper, we propose a Dynamic Network Quantization (DNQ) framework which is composed of two modules: a…

Despite the success of convolutional neural networks (CNNs) in many academic benchmarks for computer vision tasks, their application in the real-world is still facing fundamental challenges. One of these open problems is the inherent lack…

While deep convolutional neural networks (CNNs) are vulnerable to adversarial attacks, considerably few efforts have been paid to construct robust deep tracking algorithms against adversarial attacks. Current studies on adversarial attack…

Mixed precision quantization has become an important technique for optimizing the execution of deep neural networks (DNNs). Certified robustness, which provides provable guarantees about a model's ability to withstand different adversarial…

While neural networks have advanced the frontiers in many applications, they often come at a high computational cost. Reducing the power and latency of neural network inference is key if we want to integrate modern networks into edge…

Deep Neural Networks (DNNs) are highly sensitive to imperceptible malicious perturbations, known as adversarial attacks. Following the discovery of this vulnerability in real-world imaging and vision applications, the associated safety…

Large language models (LLMs) are increasingly deployed on edge devices under strict computation and quantization constraints, yet their security implications remain unclear. We study query-based knowledge extraction from quantized…

Deep neural network (DNN) quantization for fast, efficient inference has been an important tool in limiting the cost of machine learning (ML) model inference. Quantization-specific model development techniques such as regularization,…

Radar sensors are crucial for environment perception of driver assistance systems as well as autonomous vehicles. Key performance factors are weather resistance and the possibility to directly measure velocity. With a rising number of radar…

Deep Neural Networks (DNNs) typically require massive amount of computation resource in inference tasks for computer vision applications. Quantization can significantly reduce DNN computation and storage by decreasing the bitwidth of…

Deep Neural Networks (DNNs) have been shown to be vulnerable against adversarial examples, which are data points cleverly constructed to fool the classifier. Such attacks can be devastating in practice, especially as DNNs are being applied…

Radar sensors are crucial for environment perception of driver assistance systems as well as autonomous vehicles. With a rising number of radar sensors and the so far unregulated automotive radar frequency band, mutual interference is…

Recent advancements in machine learning achieved by Deep Neural Networks (DNNs) have been significant. While demonstrating high accuracy, DNNs are associated with a huge number of parameters and computations, which leads to high memory…

Deep neural networks (DNNs) are state-of-the-art algorithms for multiple applications, spanning from image classification to speech recognition. While providing excellent accuracy, they often have enormous compute and memory requirements.…

Although considerable progress has been obtained in neural network quantization for efficient inference, existing methods are not scalable to heterogeneous devices as one dedicated model needs to be trained, transmitted, and stored for one…

High-performance Deep Neural Networks (DNNs) are increasingly deployed in many real-world applications e.g., cloud prediction APIs. Recent advances in model functionality stealing attacks via black-box access (i.e., inputs in, predictions…