Related papers: ModelDiff: Testing-Based DNN Similarity Comparison…
Due to the widespread application of deep neural networks~(DNNs) in safety-critical tasks, deep learning testing has drawn increasing attention. During the testing process, test cases that have been fuzzed or selected using test metrics are…
Malicious users attempt to replicate commercial models functionally at low cost by training a clone model with query responses. It is challenging to timely prevent such model-stealing attacks to achieve strong protection and maintain…
Adversarial samples exploit irregularities in the manifold `learned' by deep learning models to cause misclassifications. The study of these adversarial samples provides insight into the features a model uses to classify inputs, which can…
Deep neural networks (DNNs) have achieved remarkable success in a variety of computer vision tasks, where massive labeled images are routinely required for model optimization. Yet, the data collected from the open world are unavoidably…
Context: Automated software defect prediction (SDP) methods are increasingly applied, often with the use of machine learning (ML) techniques. Yet, the existing ML-based approaches require manually extracted features, which are cumbersome,…
Overcoming fiber nonlinearity is one of the core challenges limiting the capacity of optical fiber communication systems. Machine learning based solutions such as learned digital backpropagation (LDBP) and the recently proposed deep…
Recent increases in the computational demands of deep neural networks (DNNs) have sparked interest in efficient deep learning mechanisms, e.g., quantization or pruning. These mechanisms enable the construction of a small, efficient version…
As backdoor attacks become more stealthy and robust, they reveal critical weaknesses in current defense strategies: detection methods often rely on coarse-grained feature statistics, and purification methods typically require full…
Deep neural networks (DNNs) achieve state-of-the-art results in a variety of domains. Unfortunately, DNNs are notorious for their non-interpretability, and thus limit their applicability in hypothesis-driven domains such as biology and…
Deep neural networks (DNNs) are poorly calibrated when trained in conventional ways. To improve confidence calibration of DNNs, we propose a novel training method, distance-based learning from errors (DBLE). DBLE bases its confidence…
Deep learning (DL) models have become increasingly popular in identifying software vulnerabilities. Prior studies found that vulnerabilities across different vulnerable programs may exhibit similar vulnerable scopes, implicitly forming…
In this paper we introduce the DMR -- a prototype-based method and network architecture for deep learning which is using a decision tree (DT)-based inference and synthetic data to balance the classes. It builds upon the recently introduced…
Neural networks are powering the deployment of embedded devices and Internet of Things. Applications range from personal assistants to critical ones such as self-driving cars. It has been shown recently that models obtained from neural nets…
Many learning algorithms such as kernel machines, nearest neighbors, clustering, or anomaly detection, are based on the concept of 'distance' or 'similarity'. Before similarities are used for training an actual machine learning model, we…
Deep learning achieves remarkable performance on pattern recognition, but can be vulnerable to defects of some important properties such as robustness and security. This tutorial is based on a stream of research conducted since the summer…
One of the challenging problems in digital image forensics is the capability to identify images that are captured by the same camera device. This knowledge can help forensic experts in gathering intelligence about suspects by analyzing…
Recent advancements in semi-supervised deep learning have introduced effective strategies for leveraging both labeled and unlabeled data to improve classification performance. This work proposes a semi-supervised framework that utilizes a…
We introduce a model-based image reconstruction framework with a convolution neural network (CNN) based regularization prior. The proposed formulation provides a systematic approach for deriving deep architectures for inverse problems with…
This proposes a novel ensemble deep learning-based model to accurately classify, detect and localize different defect categories for aggressive pitches and thin resists (High NA applications).In particular, we train RetinaNet models using…
There are significant benefits to serve deep learning models from relational databases. First, features extracted from databases do not need to be transferred to any decoupled deep learning systems for inferences, and thus the system…