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 54 for “"Adversarial Examples"”.
-
Adversarial Examples in Simpler Settings
In this thesis we explore adversarial examples for simple model families and simple data distributions, focusing in particular on linear and kernel classifiers. On the theoretical front we find evidence that natural accuracy and robust accuracy are more likely than not to be misaligned. We conclude …
-
DYNAMIC DEFENSES AND THE TRANSFERABILITY OF ADVERSARIAL EXAMPLES
Adversarial machine learning has been an important area of study for the securing of machine learning systems. However, for every defense that is made to protect these artificial learners, a more sophisticated attack emerges to defeat it. This has created an arms race, with the problem of …
-
Adversarial Examples and Distribution Shift: A Representations Perspective
Adversarial attacks cause machine learning models to produce wrong predictions by minimally perturbing their input. In this thesis, we take a step towards understanding how these perturbations affect the intermediate data representations of the model. Specifically, we compare standard and …
-
Contrasting with adversarial examples improves self-supervised representation learning
DSpace SAF Submission Ingestion Package generated from Vireo submission #18414 on 2022-11-16 at 10:56:42
-
Usage of Adversarial Examples as a Defensive Mechanism in Cybersecurity
… to secure data and information. We propose that adversarial examples can be used as a defensive mechanism to protect secure information from these GUI-Attacks. We hope to prove that these adversarial examples can be used to prevent malicious AI from being able to recognize the icons for popular …
-
Evaluating Adversarial Robustness of Detection-based Defenses against Adversarial Examples
… it has been shown that they are vulnerable to adversarial attacks, a set of techniques that violate the integrity, confidentiality, or availability of such systems. In particular, one of the most studied phenomena concerns adversarial examples, i.e., input samples that are carefully manipulated …
-
Multi-model-based defense against adversarial examples for neural networks
… models have been found to be vulnerable to adversarial examples, i.e., carefully crafted examples aiming to mislead machine learning models. Adversarial examples can pose potential risks on safety/security-critical applications. Existing defense approaches are still vulnerable to emerging …
-
Towards machine learning models robust to adversarial examples and backdoor attacks
… two major modes of brittleness of such systems: adversarial examples and backdoor data poisoning attacks. Specifically, in the first part of the thesis, we build a methodology for defending against adversarial examples that is the first one to provide non-trivial adversarial robustness against an …
-
On Transferability of Adversarial Examples on Machine-Learning-Based Malware Classifiers
… vulnerable and sensible to transferable adversarial example (AE) attacks. The transfer AE attack does not require extra information from the victim model such as gradient information. Researchers explore mainly 2 lines of transfer-based adversarial example attacks: ensemble models and …
-
On Passive-Scoping as a method for Large Language Model Robustness to Jailbreaks and Adversarial Examples
… models (LLMs) not only present a challenge for adversarial robustness, but also the natural emergence of unwanted capabilities. Current approaches to safeguarding AI and LLMs predominantly rely on explicitly restricting known instances of these. However, this places a burden on model developers, …
-
Adversarial machine learning in computer vision: attacks and defenses on machine learning models
… networks are demonstrated to be vulnerable to adversarial examples at the test time. Adversarial examples are malicious inputs generated from the legitimate inputs by adding small perturbations in order to fool machine learning models to misclassify. We mainly aim to answer two research …
-
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 …
-
Attacking Computer Vision Models Using Occlusion Analysis to Create Physically Robust Adversarial Images
… neural networks are susceptible to simple adversarial inputs. As there is no overlap between the optical illusions that fool humans and the adversarial examples that threaten convolutional neural networks, little is understood as to why these adversarial examples dupe such advanced models …
-
Robustifying Machine Learning based Security Applications
… — attackers can manipulate the inputs (i.e., adversarial examples) to cause machine learning models to make a mistake, and it's very challenging to obtain a large amount of attackers' data. These make applying machine learning in security-critical applications difficult. In this dissertation, …
-
On practical robustness of machine learning systems
… We consider these systems' vulnerability to adversarial examples--subtle, crafted perturbations to inputs which induce large change in output. We show that these adversarial examples are not only theoretical concern, by desigining the first 3D adversarial objects, and by demonstrating that …
-
Understanding the landscape of adversarial robustness
… models are pervasively vulnerable to adversarial examples. Adversarial examples are inputs that have been slightly perturbed--such that the semantic content is the same--as to cause malicious behavior in a classifier. The study of adversarial robustness has so far largely focused on …
-
Adversarial methods in machine learning - a federated defense and an attack
… Unfortunately, neural networks are vulnerable to adversarial examples — inputs that are almost indistinguishable from natural data and yet elicit misclassification from the network. The focus of this thesis is to investigate the space of adversarial examples in hitherto novel applications. We …
-
Towards Robust Deep Neural Networks
… to attacks, such as Trojans during training and Adversarial Examples at test time. Adversarial Examples are inputs with carefully crafted perturbations added to benign samples. In the Computer Vision domain, while the perturbations being imperceptible to humans, Adversarial Examples can …
-
Evaluating robustness of neural networks with mixed integer programming
… However, neural networks can be fooled by adversarial examples -- slightly perturbed inputs that are misclassified with high confidence. Verification of networks enables us to gauge their vulnerability to such adversarial examples. We formulate verification of piecewise-linear neural …
-
Person Re-identification and an Adversarial Attack and Defense for Person Re-identification Networks
… improved significantly. However, latest works in adversarial machine learning have shown the vulnerabilities of DNNs against adversarial examples, which are carefully crafted images that are similar to original/benign images, but can deceive the neural network models. Neural network-based ReID …
Page 1 of 3