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 17 of 17 for “"Data Poisoning"”.
-
Provable stability defenses for targeted data poisoning
… are often trained on massive, crowdsourced datasets. Due to the impossibility of checking this data, these systems may be susceptible to data poisoning attacks where malicious users inject false training data in order to influence the learned model. While recent work has focused primarily on …
-
Logic-Targeted Data Poisoning and Cascading Failures in AI-Driven Distributed Traffic Control Systems
MARL (multi-agent reinforcement learning) is increasingly used to create intelligent traffc signal control systems for city-wide traffc management. This improves the movement of people and vehicles, but it also introduces new physical-layer safety risks at the sensor level that have not been …
-
Towards machine learning models robust to adversarial examples and backdoor attacks
… such systems: adversarial examples and backdoor data poisoning attacks. Specifically, in the first part of the thesis, we build a methodology for defending against adversarial examples that is the first one to provide non-trivial adversarial robustness against an adaptive adversary. In the second …
-
Deep Neural Network for Anomaly Detection
… to deal with new/unknown attacks, imbalanced data, the lack of labelled data, and the vulnerability to data poisoning attacks. First, to detect new/unknown anomalies (attacks) effectively, the thesis proposes a novel representation learning method, i.e., AutoEncoders (AEs) based models, that …
-
H2OGAN: A Deep Learning Approach for Detecting and Generating Cyber-Physical Anomalies
… introduces security vulnerabilities, such as data poisoning. In this context, data poisoning could involve the malicious manipulation of critical data, including water quality parameters, flow rates, and chemical composition levels. The consequences of such threats are significant, potentially …
-
Building and using robust representations in image classification
… high-level feature representations of complex data. These learned representations obviate manual data pre-processing, and are versatile enough to generalize across tasks. However, they are not yet capable of fully capturing abstract, meaningful features of the data. For instance, the …
-
Metagradient Descent: Differentiating Large-Scale Training
… descent (MGD), we greatly improve on existing dataset selection methods, outperform accuracy-degrading data poisoning attacks by an order of magnitude, and automatically find competitive learning rate schedules.
-
Understanding and Mitigating Data-Centric Vulnerabilities in Modern AI Systems
… (AI) systems, trained on vast internet-scale datasets, demonstrate remarkable performance and emergent capabilities. However, this reliance on large datasets that are expensive or difficult to quality-control exposes AI systems to critical vulnerabilities, including data poisoning, backdoor …
-
Adversarial Resilient and Privacy Preserving Deep learning
… and cognitive machine intelligence, ranging from data poisoning and model inversion during the training phase and adversarial evasion attacks during model inference phase, aiming to cause the well-trained model to misbehave randomly or purposefully. This dissertation research addresses these …
-
Protecting vehicles from cyberattacks: context aware AI-based intrusion detection for vehicle CAN bus security.
… controller area network (CAN) bus for real-time data exchange. However, the CAN bus lacks security measures, rendering it susceptible to cyberattacks, endangering passenger safety. Although artificial intelligence (AI)-based intrusion detection systems (IDSs) can detect these attacks, achieving …
-
Multiagent Approaches to Enhance Learning and Trust in AI Systems
… as thresholded Borda count to defend against data poisoning in ensemble learning. Taken together, these contributions show how multiagent approaches can enhance both learning and trust, offering a pathway to AI systems that are capable, transparent, and reliable in practice.
-
An Axiomatic Perspective on Anomaly Detection
… extend infinitely far away from the training data. Additionally, we experimentally demonstrate that another common method, Local Outlier Factor, is vulnerable to adversarial data poisoning. To conduct these experimental evaluations, a tool for dataset generation, experimentation and …
-
High-performance computing for smart grid analysis and optimization
… statistical methods, are vulnerable to training data poisoning. We build and implement a first-of-its-kind data poisoning strategy that is effective at corrupting the forecasting model even in the presence of outlier detection. Our method applies to several forecasting models, including the most …
-
Principled approaches to robust machine learning and beyond
… of a small number of adversarially added data points. Both algorithms are the first efficient algorithms which achieve (nearly) optimal error bounds for a number fundamental statistical tasks such as mean estimation and covariance estimation. The goal of this thesis is to present these two …
-
Privacy Attacks and Defenses under Security Threats in Machine Learning
… or model owners, including recovering training data, inferring membership, and cloning the trained model without authentication. In terms of security, the functionality of machine learning models might be disrupted by malicious users. Both types of attacks pose challenges to the widespread …
-
Approximate Inference: New Visions
… and be less vulnerable to attacks such as data poisoning. Critically, the success of Bayesian methods in practice, including the recent resurgence of Bayesian deep learning, relies on fast and accurate approximate Bayesian inference applied to probabilistic models. These approximate …
-
Towards Trustworthy Learning in Temporal Learning Environments
… benchmarks and into real-world settings, where data distributions shift, environments change, and objectives evolve, it is more important and difficult to ensure consistent and reliable behavior. Yet, most existing methods for safety and robustness are designed for models trained on fixed …