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 6 of 6 for “"adversarial ML"”.
-
Exploring Defenses Against Adversarial Attacks in Machine Learning-Based Malware Detection
Machine learning (ML) has facilitated progress in several disciplines as a result of greater resources, data volumes, and algorithmic developments. Particularly in cybersecurity, ML-based malware detection has proven to be an effective method of classifying software executables as benign or …
-
Understanding, Fortifying and Democratizing AI Security
… of AI in our everyday lives. A growing body of adversarial machine learning research has revealed that deep neural networks — the workhorse of modern AI applications — are extremely vulnerable to adversarial examples. These are malicious inputs crafted by an attacker that can completely confuse …
-
Resilient Machine Learning (rML) Development Environment Against Adversarial Attacks
Machine learning (ML) algorithms have been widely used in many critical automated systems, including Dynamic Data Driven Applications Systems (DDDAS)-financial trading, autonomous vehicles, and intrusion detection systems. However, malicious adversaries have strong interests in manipulating the …
-
Analyzing and Detecting Internet of Things Malware Using Residual Static Graph- and String-Based Artifacts
… analysis of malicious graphs. Machine Learning (ML) algorithms are actively used in the process of detecting and classifying malicious software. Toward detection, we use different CFG-based features as mentioned above, and augment them with CFGs of the benign dataset and build a detection system. …
-
DATA PARTITIONING AND COMPENSATION TECHNIQUES FOR SECURE TRAINING OF MACHINE LEARNING MODELS
Advances in Machine Learning (ML), coupled with increased availability of huge amounts of data collected from diverse sources and improvements in computing power, have led to a widespread adoption of ML-based solutions in critical application scenarios. However, ML models intrinsically introduce …
-
Adversarial robustness in advanced machine learning models integrating graph neural networks and large language models
… in relational reasoning but are vulnerable to adversarial manipulation and lack interpretability, while LLMs are strong in linguistic reasoning and generalization yet struggle with relational data and inherent security risks.</p><p>This dissertation introduces a unified framework that …