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 12 of 12 for “"Data Poisoning Attack"”.
-
Game Theoretic Analysis of Defence Algorithms Against Data Poisoning Attack
… solve a wide variety of tasks in today’s world, data poisoning attack poses a significant threat to ML applications. Although numerous defence algorithms against data poisoning attack have been proposed and shown to be effective, most defence algorithms are analyzed under the assumption of fixed …
-
Adversarial and Data Poisoning Attacks against Deep Learning
… However, recent studies on adversarial attacks and data poisoning attacks show that deep learning models are vulnerable to these attacks. In this dissertation, we focus on a special type of data poisoning attack, triggerless clean-label data poisoning attacks. In such an attack, some …
-
Defeat data poisoning attacks on facial recognition applications
… of use cases for facial images, adversaries will attack these applications for profit. This dissertation focuses on two major applications of facial photos: facial authentication and deepfakes. Facial authentication has become increasingly popular on personal devices. Due to the ease of use, it …
-
Detecting targeted data poisoning attacks on deep neural networks
… use, there have been many works that focus on attacking such DNN-based systems for nefarious purposes. One type of attack on DNNs is called a "targeted data poisoning" attack, which has the goal of injecting photos into the DNNs training set in such a way as to cause the DNN to learn malicious …
-
Securing Smart Agriculture with Communication-efficient Federated Unlearning
This thesis addresses the data poisoning attack in smart agricultural systems using federated unlearning, where the contribution of compromised field devices must be removed from the global model under communication constraints. We propose FedSCAN, a three-phase framework that identifies critical …
-
Veracity and Vulnerabilities Analysis of Multi-Sourced Data
… is largely driven by the ubiquitous massive data, which are typically collected from multiple data sources. However, the multi-source data usually contains erroneous information and some errors may be caused by intentional manipulation by adversarial attackers. These issues may cause the …
-
Towards Safe and Secure Generative AI Systems
… these risks is the large-scale pre-training data, which is the cornerstone of powerful generative AI systems, such as ChatGPT and Gemini, etc.. Model-providers (e.g., OpenAI) often collect Internet-wide scale pre-training data from numerous data-owners (e.g., Wikipedia). This dissertation …
-
Data Poisoning Attacks in Transportation and Infrastructure-Enabled Defense Methods
… system is increasingly driven by massive datasets, including vehicular data (e.g., from GPS, camera and LiDAR) and infrastructure-generated data (e.g., from loop detectors and travel time sensors). However, the growing reliance on data poses potential cybersecurity issues to the …
-
Robust learning of deep neural networks under data corruption
… neural networks in the presence of corrupted data is challenging as the corrupted data points may significantly impact generalization performance of the models. Unfortunately, the data corruption issue widely exists in many application domains, including but not limited to, healthcare, …
-
Machine Learning in Industry: Applications and Security Challenges
… systems introduces security challenges such as data poisoning attacks, adversarial attacks, model stealing attacks, and membership inference attacks. To address these concerns, we investigate the reliability and robustness of the crack detection system. Specifically, we design a backdoor attack, …
-
Exploring Poisoning Effects on Deep Learning
… advances. With sufficient high-quality training data, correct implementations, and benign training environments, deep learning can achieve superior accuracy than traditional machine learning techniques. However, in practice, the massive training data may come from untrusted sources, where some …
-
Trustworthy Machine Learning with Data in the Wild
… models trained on extensive internet-collected datasets. While this approach has yielded remarkable capabilities, it introduces critical vulnerabilities: training data can be untrustworthy, containing harmful content or becoming susceptible to data poisoning attacks. In such scenarios, model …