Related papers: Probing Model Signal-Awareness via Prediction-Pres…
In this paper we present a linear programming solution for sign pattern recovery of a sparse signal from noisy random projections of the signal. We consider two types of noise models, input noise, where noise enters before the random…
Quantization is a promising approach for reducing memory overhead and accelerating inference, especially in large pre-trained language model (PLM) scenarios. While having no access to original training data due to security and privacy…
This research proposes a machine learning-based attack detection model for power systems, specifically targeting smart grids. By utilizing data and logs collected from Phasor Measuring Devices (PMUs), the model aims to learn system…
Learning from Noisy Labels (LNL) remains a fundamental challenge in deep learning because real-world datasets often contain corrupted annotations. Most existing methods rely on label correction or sample selection mechanisms. In contrast,…
This paper proposes novel spectrum sensing algorithms for cognitive radio networks. By assuming known transmitter pulse shaping filter, synchronous and asynchronous receiver scenarios have been considered. For each of these scenarios, the…
We consider the problem of reconstructing a signal from under-determined modulo observations (or measurements). This observation model is inspired by a (relatively) less well-known imaging mechanism called modulo imaging, which can be used…
This paper proposes a novel learning to learn method, called learning to learn iterative search algorithm (LISA), for signal detection in a multi-input multi-output (MIMO) system. The idea is to regard the signal detection problem as a…
Membership inference attacks (MIA) try to detect if data samples were used to train a neural network model, e.g. to detect copyright abuses. We show that models with higher dimensional input and output are more vulnerable to MIA, and…
In this paper, we focus on semi-supervised object detection to boost performance of proposal-based object detectors (a.k.a. two-stage object detectors) by training on both labeled and unlabeled data. However, it is non-trivial to train…
Purpose: Many useful image quality metrics for evaluating linear image reconstruction techniques do not apply to or are difficult to interpret for non-linear image reconstruction. The vast majority of metrics employed for evaluating…
While deep learning models have shown significant performance across various domains, their deployment needs extensive resources and advanced computing infrastructure. As a solution, Machine Learning as a Service (MLaaS) has emerged,…
Model compression by way of parameter pruning, quantization, or distillation has recently gained popularity as an approach for reducing the computational requirements of modern deep neural network models for NLP. Inspired by prior works…
Image restoration algorithms such as super resolution (SR) are indispensable pre-processing modules for object detection in low quality images. Most of these algorithms assume the degradation is fixed and known a priori. However, in…
Sharpness-Aware Minimization (SAM) optimizer enhances the generalization ability of the machine learning model by exploring the flat minima landscape through weight perturbations. Despite its empirical success, SAM introduces an additional…
Deep neural networks (DNNs) often suffer from the overconfidence issue, where incorrect predictions are made with high confidence scores, hindering the applications in critical systems. In this paper, we propose a novel approach called…
Increasing use of ML technologies in privacy-sensitive domains such as medical diagnoses, lifestyle predictions, and business decisions highlights the need to better understand if these ML technologies are introducing leakages of sensitive…
We propose a neural network-based approach that computes a stable and generalizing metric (LSiM) to compare data from a variety of numerical simulation sources. We focus on scalar time-dependent 2D data that commonly arises from motion and…
Lidar-based SLAM systems are highly sensitive to adverse conditions such as occlusion, noise, and field-of-view (FoV) degradation, yet existing robustness evaluation methods either lack physical grounding or do not capture sensor-specific…
Sharpness-Aware Minimization (SAM) is widely used to seek flatter minima -- often linked to better generalization. In its standard implementation, SAM updates the current iterate using the loss gradient evaluated at a point perturbed by…
Numerous safety- or security-critical systems depend on cameras to perceive their surroundings, further allowing artificial intelligence (AI) to analyze the captured images to make important decisions. However, a concerning attack vector…