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 83 for “"Adversarial Attacks."”.
-
Adversarial attacks and defenses for generative models
Adversarial Machine learning is a field of research lying at the intersection of Machine Learning and Security, which studies vulnerabilities of Machine learning models that make them susceptible to attacks. The attacks are inflicted by carefully designing a perturbed input which appears benign, …
-
Hardening DGA Classifiers Using Adversarial Attacks and IVAP
… This thesis consists of two parts: the use of adversarial attacks to harden DGA classifiers against CharBot and the use of Inductive Venn-Abers Predictors (IVAP) to raise classifiers' predictive scores.
-
Adversarial Attacks on Natural Language and Speech Processing Models
… deep learning models are vulnerable to adversarial attacks. A deliberate and specific perturbation of a clean input sample can create an adversarial example, which, when processed by the model, leads to incorrect predictions. Such vulnerabilities can be exploited by malicious adversaries …
-
Securing Multi-Layer Federated Learning: Detecting and Mitigating Adversarial Attacks
Within the realm of federated learning (FL), adversarial entities can poison models, slowing down or destroying the FL training process. Therefore, attack prevention and mitigation are crucial for FL. Real-world scenarios may necessitate additional separation or abstraction between clients and …
-
ACADIA: Efficient and Robust Adversarial Attacks Against Deep Reinforcement Learning
Existing adversarial algorithms for Deep Reinforcement Learning (DRL) have largely focused on identifying an optimal time to attack a DRL agent. However, little work has been explored in injecting efficient adversarial perturbations in DRL environments. We propose a suite of novel DRL adversarial …
-
Local approximations of deep learning models for black-box adversarial attacks
We study the problem of generating adversarial examples for image classifiers in the black-box setting (when the model is available only as an oracle). We unify two seemingly orthogonal and concurrent lines of work in black-box adversarial generation: query-based attacks and substitute models. In …
-
Unmasking Deepfakes, Adversarial Attacks, and Mobile Users in The Deep Learning Era
… to be aware of those generated by targeted attacks. Focusing on voice disorder detection systems, which are becoming increasingly important in public health, machine learning is increasingly present and crucial in distinguishing between healthy and pathological voices. A significant concern, …
-
Defending distributed systems against adversarial attacks: consensus, consensus-based learning, and statistical learning
… distributed systems and their vulnerability to adversarial attacks, it is crucial to design systems that are provably secured. In this dissertation, we propose and explore the problems of performing consensus, consensus-based learning, and statistical learning in the presence of malicious …
-
In the Shadow of Prompts: Adversarial Attacks and Model Cloning in Large Language Models
<p>Large-language models (LLMs) already power mission critical tasks such as command-and-control chat, satellite ground-station automation, military analytics, and cyber-defense. Since most of these services are offered through application programming interfaces (APIs) that still expose full or …
-
A System for the Detection of Adversarial Attacks in Computer Vision via Performance Metrics
<p>Adversarial attacks, or attacks committed by an adversary to hijack a system, are prevalent in the deep learning tasks of computer vision and are one of the greatest threats to these models' safe and accurate use. These attacks force the trained model to misclassify an image, using pixel-level …
-
Finite Gaussian Neurons: Defending Against Adversarial Attacks by Making Neural Networks Say "I Don’t Know"
… neural networks aimed at protecting against adversarial attacks.<br />Since 2014, artificial neural networks have been known to be vulnerable to adversarial attacks, which can fool the network into producing wrong or nonsensical outputs by making humanly imperceptible alterations to inputs. …
-
An evaluation of the robustness of the natural-adversarial mutual information-based defense and malware classification against adversarial attacks for deep learning
… way. These modified samples are known as adversarial examples and have been crafted with the goal of causing the target DNN to modify its behavior. It has been shown that adversarial examples can be crafted even when the attacker does not have access to the training parameters and model …
-
GENERALIZING ROBUSTNESS VERIFICATION FOR MACHINE LEARNING
… the robustness of DNN’s to ℓₚ norm bounded adversarial attacks there are still a few gaps between available guarantees and those needed in practice. In this thesis we focus on resolving two of these limitations. 1)While current verification methods mainly focus on the ℓₚ-norm threat model of …
-
ENHANCING DEEP LEARNING WITH SYMBOLIC DOMAIN KNOWLEDGE
… that deep neural networks are vulnerable to adversarial attacks. In the second part of the thesis, we propose to leverage prior knowledge to defend against adversarial attacks in RL settings using the Knowledge-based Policy Recycling (KPR) framework.
-
Mathematical Optimization Algorithms for Model Compression and Adversarial Learning in Deep Neural Networks
… issue of model size, DNNs are also sensitive to adversarial attacks, a small invisible noise on the input data can fully mislead a DNN. Research on the robustness of DNNs follows two directions in general. The first is to enhance the robustness of DNNs, which increases the degree of difficulty …
-
Multimodal Foundation Models through the Lens of Security: Robust Deepfake Detection and Adversarial Resilience
… deepfake images and are also vulnerable to adversarial attacks that degrade their performance. These threats contribute to the spread of misinformation and the manipulation of AI systems, raising serious concerns about their security and reliability. This thesis explores robust detection …
-
Lightweight intrusion detection of attacks on the Internet of Things (IoT) in critical infrastructures.
… and deparameterized. 3) Resilience Against Adversarial Attacks: Adversarial training with semi-supervised learning enhanced the OCFSDA model's resilience against adversarial attacks. The model was further optimized using quantization techniques. 4) Performance Evaluation: Experimental …
-
Adversarial Learned Soups: neural network averaging for joint clean and robust performance
To make computer vision models more adversarially robust, recent literature has made various additions to the adversarial training process, from alternative adversarial losses to data augmentations to the usage of large numbers of diffusion-generated synthetic samples. However, models trained for …
-
Certifying robustness in inference and learning problems
… irrelevant or unrecognizable inputs, and adversarial attacks from unknown sources. The underlying theme connecting the topics studied in this dissertation is the development of learning algorithms robust to such unexpected, potentially harmful, deviations. Broadly, three problems in robust …
Page 1 of 5