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 133 for “"Adversarial Attack"”.
-
Transportability of Adversarial Attack
… machine learning algorithms to introduce adversarial cloaks, or noise, into images containing real individuals and assess whether the resulting images still accurately represent human subjects. Specifically, I seek to discern whether images featuring avatars, placed in the same spatial …
-
Adversarial Attack and Defense
… while the robustness of Deep Learning models in adversarial settings was not well-studied until recently. Recent work shows that Deep Learning is vulnerable to a new type of attacks, called adversarial attack, where adversaries can manipulate deep-learning outputs by adding imperceptible …
-
Detecting and Mitigating Adversarial Attack
… convolutional neural networks are susceptible to adversarial examples as well that can also misclassify ECG signals. Moreover, they do not generalize well on the out-of-distribution dataset. Adversarial attacks are small crafted perturbations injected in the original data which manifest the …
-
Adversarial Attack and Defense in Time Series Classification
… to a range of security threats, including adversarial and backdoor attacks, and face limitations in certified defense and architectural robustness. This thesis addresses four interrelated challenges in robust and secure TSC, with each contributing to a deeper understanding of …
-
Adversarial Attack and Robust Learning in Multi-Arm Bandit Problems
… one of these cases. Particularly, we purpose an attack that is oblivious to algorithm's behavior and show that the attack can completely manipulate many typical bandit algorithms. Next we purpose an algorithm that is simultaneously robust to both types of adversaries and efficiently utilize side …
-
TROPICAL GEOMETRY IN NEURAL NETWORKS: A NOVEL DEFENSE AGAINST ADVERSARIAL ATTACK
… though powerful, are highly susceptible to adversarial attacks, which can severely impact their reliability and performance in critical applications, especially within the Department of Defense (DoD). This thesis employs Tropical Convolutional Neural Networks (TCNN), a novel technique …
-
Invernet: An Adversarial Attack Framework to Infer Downstream Context Distribution through Word Embedding Inversion
… issue can rise during this process is that the adversarial parties who have the pre-train datasets may be able infer the key information such context distribution of downstream datasets by analyzing the fine-tuned embeddings. In this study, we aim to propose an effective way to infer the context …
-
Targeted Adversarial Attacks against Neural Network Trajectory Predictors
… of works studying their robustness against adversarially crafted input trajectories. To bridge this gap, in this paper, we propose a targeted adversarial attack against DNN models for trajectory forecasting tasks. We call the proposed attack TA4TP for Targeted adversarial Attack for …
-
Post-hoc explainable semantic image segmentation: applications for interpretability and adversarial attacks /
… interpretability in semantic segmentation and adversarial attack scenarios. It proposes and investigates three explainability method extensions: occlusion-based, activation perturbation-based, and gradient-based approaches, all specifically designed for segmentation tasks. These methods are …
-
Robustness of Trajectory Prediction Neural Network Models
… satisfactory robustness in dealing with purposed adversarial attacks. In this paper, we propose an adversarial attack approach against trajectory prediction models that use conformal prediction to provide verification of deep neural network model prediction. While satisfying the assumption of …
-
Adversarial Machine Learning in Wireless Communication Systems
We consider adversarial machine learning settings in wireless communication systems with adversaries that attempt to manipulate the deep learning (DL)-based wireless communication tasks, such as modulation classification and signal classification. In particular, we consider the evasion attack, …
-
ADVERSARIAL ATTACKS ON UNDERWATER SOUNDSCAPE CLASSIFICATION SYSTEMS
… (UUV). CNNs are known to be vulnerable to adversarial attacks that add a small perturbation to the input, causing a classifier to incorrectly classify the input example. A common method in audio classification is to transform source audio into spectrogram images to use as features for …
-
Learning Transferable Representations for Visual Recognition
… learning, domain adaptation, and generalizable adversarial attack. By zero-shot learning, we enable models to predict labels not seen in the training phase. By domain adaptation, we improve a model's performance on the target domain by mitigating its discrepancy from a labeled source model, …
-
On Inference-Time Adversaries in Object Detection Models
… models could wreck havoc if loopholes are found. Adversarial attack algorithms have been shown to cause deep neural networks to fail on image classification and object detection tasks while being visually imperceptible to humans. Adversarial attacks cause out of distribution predictions and can …
-
AI-infused security: Robust defense by bridging theory and practice
… three interrelated research thrusts. (1) Adversarial Attack and Defense of Deep Neural Networks: We discover vulnerabilities of deep neural networks in real-world settings and the countermeasures to mitigate the threat. We develop ShapeShifter, the first targeted physical adversarial …
-
Detecting Manipulated and Adversarial Images: A Comprehensive Study of Real-world Applications
… any malicious or benign direction. Additionally, adversarial attacks targeting deep learning models pose a severe risk to computer vision applications. This dissertation explores ways of detecting and resisting manipulated or adversarial attack images. The first contribution evaluates perceptual …
-
On properties of deep cascade learning on medical imaging problems
… that models trained in this way may be easier to attack in an adversarial attack setting. We show that this is indeed true through our data showing cascade-trained models are more vulnerable than E2E models under adversarial attack. However, when trained adversarially, both architectures recover …
-
Μέθοδοι μηχανικής μάθησης για σημασιολογική ανάλυση βίντεο
… problems of privacy protection and robustness to adversarial attacks. Supervised, semi-supervised and deep learning algorithms were proposed, in the context of one-class classification, multiclass classification, adversarial attacks and defenses. Novel methodologies that provide increased …
Page 1 of 7