3 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 3 / 3
Yayın Using uncertainty metrics in adversarial machine learning as an attack and defense tool(Işık Ünivresitesi, 2022-12-19) Tuna, Ömer Faruk; Eskil, Mustafa Taner; Işık Üniversitesi, Lisansüstü Eğitim Enstitüsü, Bilgisayar Mühendisliği Doktora ProgramıDeep Neural Network (DNN) models are widely renowned for their resistance to random perturbations. However, researchers have found out that these models are indeed extremely vulnerable to deliberately crafted and seemingly imperceptible perturbations of the input, defined as adversarial samples. Adversarial attacks have the potential to substantially compromise the security of DNN-powered systems and posing high risks especially in the areas where security is a top priority. Numerous studies have been conducted in recent years to defend against these attacks and to develop more robust architectures resistant to adversarial threats. In this thesis study, we leverage the use of various uncertainty metrics obtained from MC-Dropout estimates of the model for developing new attack and defense ideas. On defense side, we propose a new adversarial detection mechanism and an uncertaintybased defense method to increase the robustness of DNN models against adversarial evasion attacks. On the attack side, we use the quantified epistemic uncertainty obtained from the model’s final probability outputs, along with the model’s own loss function, to generate effective adversarial samples. We’ve experimentally evaluated and verified the efficacy of our proposed approaches on standard computer vision datasets.Yayın English to Turkish machine translation using synchronous grammars(Işık Üniversitesi, 2022-06-14) Görgün, Onur; Tüysüz Erman, Ayşegül; Işık Üniversitesi, Lisansüstü Eğitim Enstitüsü, Bilgisayar Mühendisliği Doktora ProgramıMachine translation (MT) has been one of the hot topics in NLP research over recent years. However, most of the related studies have been done for specific languages, and there are a limited number of comprehensive studies for languages with free word order, such as Turkish. English-Turkish is also one of the least frequently studied language pairs in translation due to the morphological and syntactic gaps between the two languages. This also makes it hard to build parallel corpora, which is crucial for the machine translation task. This thesis aims to be the first statistical syntax tree-based machine translation approach to the English-Turkish language pair, as well as a parallel corpus for translation tasks. We construct an English-Turkish parallel treebank of approximately 17K sentences by following a three-phased approach: manual transformation of English trees from Penn Treebank (PTB) by constraining the translated trees to the reordering of the children and gloss replacement; morphological analysis of the translated gloss; and morphological enrichment of the target tree. For translation consistency, we also developed a set of tools. We also apply the transformation schema to the closed-domain and build 8.3K sentences corpus. We employ both corpora on machine translation task. In our experiments, we obtained a 12.8 BLEU score in the open-domain and a 26.8 BLEU score in the closed-domain. We also evaluate both corpora intrinsically through perplexity analysis. The results show that our studies on making a corpus can be repeated, and studies on machine translation using the small corpus look promising.Yayın Object recognition with competitive convolutional neural networks(Işık Üniversitesi, 2023-06-12) Erkoç, Tuğba; Eskil, M. Taner; Işık Üniversitesi, Lisansüstü Eğitim Enstitüsü, Bilgisayar Mühendisliği Doktora Programı; Işık University, School of Graduate Studies, Ph.D. in Computer EngineeringIn recent years, Artificial Intelligence (AI) has achieved impressive results, often surpassing human capabilities in tasks involving language comprehension and visual recognition. Among these, computer vision has experienced remarkable progress, largely due to the introduction of Convolutional Neural Networks (CNNs). CNNs are inspired by the hierarchical structure of the visual cortex and are designed to detect patterns, objects, and complex relationships within visual data. One key advantage is their ability to learn directly from pixel values without the need for domain expertise, which has contributed to their popularity. These networks are trained using supervised backpropagation, a process that calculates gradients of the network’s parameters (weights and biases) with respect to the loss function. While backpropagation enables impressive performance with CNNs, it also presents certain drawbacks. One such drawback is the requirement for large amounts of labeled data. When the available data samples are limited, the gradients estimated from this limited information may not accurately capture the overall data behavior, leading to suboptimal parameter updates. However, obtaining a sufficient quantity of labeled data poses a challenge. Another drawback is the requirement of careful configuration of hyperparameters, including the number of neurons, learning rate, and network architecture. Finding optimal values for these hyperparameters can be a time-consuming process. Furthermore, as the complexity of the task increases, the network architecture becomes deeper and more complex. To effectively train the shallow layers of the network, one must increase the number of epochs and experiment with solutions to prevent vanishing gradients. Complex problems often require a greater number of epochs to learn the intricate patterns and features present in the data. It’s important to note that while CNNs aim to mimic the structure of the visual cortex, the brain’s learning mechanism does not necessarily involve back-propagation. Although CNNs incorporate the layered architecture of the visual cortex, the reliance on backpropagation introduces an artificial learning procedure that may not align with the brain’s actual learning process. Therefore, it is crucial to explore alternative learning paradigms that do not rely on backpropagation. In this dissertation study, a unique approach to unsupervised training for CNNs is explored, setting it apart from previous research. Unlike other unsupervised methods, the proposed approach eliminates the reliance on backpropagation for training the filters. Instead, we introduce a filter extraction algorithm capable of extracting dataset features by processing images only once, without requiring data labels or backward error updates. This approach operates on individual convolutional layers, gradually constructing them by discovering filters. To evaluate the effectiveness of this backpropagation-free algorithm, we design four distinct CNN architectures and conduct experiments. The results demonstrate the promising performance of training without backpropagation, achieving impressive classification accuracies on different datasets. Notably, these outcomes are attained using a single network setup without any data augmentation. Additionally, our study reveals that the proposed algorithm eliminates the need to predefine the number of filters per convolutional layer, as the algorithm automatically determines this value. Furthermore, we demonstrate that filter initialization from a random distribution is unnecessary when backpropagation is not employed during training.
