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 9 of 9 for “"Model extraction attacks"”.
-
Securing Machine Learning: Streamlining Attacks and Defenses Under Realistic Adversary Models
… been proposed to prevent, mitigate, or detect attacks, they are either limited or ineffective against continuously evolving attack strategies due to the increased availability of ML tools, databases, and computing resources. For instance, evasion attacks that aim to fool ML systems have become …
-
Access Control and Machine Learning: Evasion and Defenses
… easier to use, or to defend against specific attacks, such as the "relay attack". Such ML applications are particularly sensitive to the recent development of "adversarial machine learning", where weaknesses in machine learning systems are exploited to undermine some security-critical …
-
On Using Embeddings for Ownership Verification of Graph Neural Networks
… have emerged as a state-of-the-art approach to model and draw inferences from large scale graph-structured data in various application settings such as social networking. The primary goal of a GNN is to learn an embedding for each graph node in a dataset that encodes both the node features and …
-
Ownership and Confidentiality in Machine Learning
Statistical and machine learning (ML) models have been the primary tools for data-driven analysis for decades. Recent theoretical progress in deep neural networks (DNNs) coupled with computational advances put DNNs at the forefront of ML in the domains of vision, audio and language understanding. …
-
Advancing ML for EDA: From Secure Data to Generative AI
… face several challenges that hinder efficient model development. First, secure data sharing remains a persistent obstacle due to confidentiality concerns among design companies, limiting the availability of large and diverse datasets. Second, the reliance on manual feature selection and …
-
HARNESSING DEEP REINFORCEMENT LEARNING: STUDIES IN ROBOTIC MANIPULATION, ENHANCED SEMANTIC SEGMENTATION, AND SECURING IMAGE CLASSIFIERS
… the research focuses on developing surrogate models capable of replicating proprietary image classification models under stringent constraints. An open-source framework integrating popular DQN extensions is introduced, demonstrating their effectiveness in enhancing attack methodologies. The …
-
Energy-efficient Resistive In-memory Computing Architectures
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-02-04 without embargo terms
-
Physical side channels in embedded hardware security : analysis and defenses
… physical side channels to defend against attacks. This dissertation first addresses the vulnerability of an ASIC AES implementation to a new side-channel attack based on localized electromagnetic analysis, which is an especially potent threat to security of embedded cryptographic …
-
Electromagnetic Side-Channel Analysis of Deep-Learning Architectures on Reconfigurable Edge Hardware
The use of Machine Learning (ML) models on edge devices has gained significant attention in recent years due to their low latency and increased privacy guarantees. Edge Artificial Intelligence (Edge AI) devices are tailored toward specific applications, and a considerable amount of resources are …