Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 33 for “"Projected gradient descent"”.
-
An Inverse-Free Projected Gradient Descent Method for the Generalized Eigenvalue Problem
… method that borrows several key ideas, including projected gradient descent, back-tracking line search, and Rayleigh-Ritz (RR) projection. We establish a convergence theory for this framework. We conduct numerical experiments to assess the performance of the proposed method in comparison to two …
-
Low-rank Matrix Estimation
… part, we demonstrates the effectiveness of the projected gradient descent algorithm. Firstly, its local convergence rate is independent of the condition number. Secondly, under conditions where the objective function is rank-2r restricted L-smooth and μ-strongly convex, with L/μ < 3, projected …
-
ADVERSARIAL ROBUSTNESS IN DEEP LEARNING NLP SYSTEMS
… effective protection and relying on multi-step projected gradient descent that prolongs training. These challenges highlight the need for more robust and efficient methods. This thesis seeks to better understand deep-learning NLP vulnerabilities by exploring symbol-based and word-level attacks …
-
Robustness of ai-driven histopathology under real-world adversarial examples
… Adversarial methods include iterative Fast Gradient Sign, Projected Gradient Descent, Salt-and-Pepper noise, and the Adversarial Watermark—Stain Shift (AWSS). Three defense strategies—Randomized Smoothing, Adversarial Training, and an Artifact Detector—are evaluated for their ability to …
-
Improved Model Poisoning Attacks and Defenses in Federated Learning with Clustering
… an effective model poisoning attack using projected gradient descent. Our empirical results show that our attack has a larger impact on the global model's accuracy than previous attacks. Motivated by this, we design a robust defense algorithm that mitigates existing poisoning attacks. Our …
-
A non-convex framework for structured non-stationary covariance recovery theory and application
… combined with iteratively re ned alternating projected gradient descent. We prove a linear convergence rate for the proposed descent scheme and establish sample complexity guarantees for the estimator. As a motivating example, we consider the neuroscience application of estimation of dynamic …
-
Robust Dynamical Step Adversarial Training Defense for Deep Neural Networks
… robustness. Researchers has stated that the ”projected gradient descent” (PGD) adversarial training method specifies a concrete security guarantee on the neural network against adversarial attacks. The model trained with PGD adversaries performs robust against several different gradient based …
-
Enhancing Resilience Against Adversarial Attacks of Deep Neural Networks Using Efficient Two-Step Adversarial Defense
… adversarial attacks and particularly that projected gradient descent (PGD) may be considered the universal first order adversary and applying the adversarial training with PGD implies resistance against many other first order attacks. However, the computational cost of the adversarial …
-
Dense subgraph detection on multi-layered networks
… optimization-based formulation, we develop the projected gradient descent algorithms that bear the following distinctive advantages. First (applicability), the model is suitable for the generally defined multi-layered networks without requirements for sharing the same set of nodes across layers …
-
Stochastic Algorithms for Large Scale Machine Learning
… are necessary for computation. Stochastic gradient descent (SGD) and its variants are well known for their practical effectiveness. Prior information can be incorporated in algorithms to improve their efficiency while maintaining convergence guarantee. In this thesis, we target a unified …
-
Evaluating Methods for Improving DNN Robustness Against Adversarial Attacks
… this thesis concludes that fast sign gradient method (FGSM) adversarial training is not great at improving robustness on a variety of attacks. Projected gradient descent (PGD) adversarial training is effective at improving DNN robustness but is time-consuming. Efficient adversarial …
-
Adversarial Robustness of Modular Autonomous Driving Agents for Lane Keeping
… digital, ℓ∞-bounded evasion attacks using Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD). Attacks are injected at different points in the pipeline to isolate perception-side (lane) and control-side (steering) vulnerabilities, including a leakage configuration that forwards …
-
Finite Gaussian Neurons: Defending Against Adversarial Attacks by Making Neural Networks Say "I Don’t Know"
… in their predictions over randomized and Fast Gradient Sign Method adversarial images when compared to classical neural networks, while maintaining high accuracy and confidence over real MNIST images. <br />To further validate the capacity of Finite Gaussian Neurons to protect from adversarial …
-
Towards safer vision-language models : modality-aware vulnerability analysis and adversarial risk assessment.
… evaluated settings. Its strong correlations with Projected Gradient Descent (PGD) (0.85–0.88) and Carlini & Wagner (C&W) (0.81–0.88) attacks provide empirical evidence that VS captures vulnerability trends associated with stronger adversarial attacks while requiring substantially lower …
-
Topics on AI Fairness Preferences in Kidney Transplantation
… was employed to analyze fairness feedback, and a projected-gradient descent algorithm is proposed to estimate social fairness preferences. For the classification model, six well-established group fairness notions from the literature were evaluated, with results indicating that accuracy equality is …
-
Adversarial Robustness of Deep Learning Models
… Our analysis attributes robust overfitting in Projected Gradient Descent (PGD)-based AT to the sign function used in PGD attacks, which results in poor expansiveness properties. We further show that similar issues extend to a broader class of PGD-like iterative attack algorithms, highlighting …
-
Query-Efficient Decision-based Attack on Image Retrieval Systems
… and combines Natural Evolution Strategy with Projected Gradient Descent for the optimization. We established the convergence of the framework and proposed several optimization techniques to further reduce the perturbation in a query-efficient manner. Our comprehensive experimental evaluation …
-
Modern Classification with Big Data
… including support vector machine, random forest, gradient boosting, and deep neural network. Chapter 3 introduces sparse penalized DWD for high-dimensional classification, which is commonly used in the era of big data. We develop a very efficient algorithm to compute the solution path of the …
-
An evaluation of the robustness of the natural-adversarial mutual information-based defense and malware classification against adversarial attacks for deep learning
… We will compare MI-Craft to standard projected gradient descent for the creation of adversarial examples, as well as demonstrate the effectiveness of MI-Craft and NAMID under the CIFAR10 and MalImg datasets.
-
Generative models and robustness in deep learning for inverse problems
… prior to solve linear inverse problems using projected gradient descent (PGD). Experiments show that our approach provides a speed-up of 60-80× over earlier GAN-based recovery methods along with better accuracy. Our main theoretical result is that if the measurement matrix is moderately …
Page 1 of 2