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 20 of 41 for “"Data poisoning attacks"”.
-
Data poisoning attacks against conformal prediction
… of such CP methods with regard to dedicated data poisoning attacks have not been studied previously. To bridge this gap, for the first time, we in this paper propose a new class of black-box data poisoning attacks against CP, where the adversary aims to cause the desired manipulations of some …
-
Vision Transformers Under Data Poisoning Attacks
… training images from public sources, but such data may be sabotaged; otherwise natural images may have subtle patterns added to them, crafted to cause a specific image to be incorrectly classified after training. Poisoning attack methods have been developed and tested on ResNets, but Vision …
-
Defending deepfake detector against data poisoning attacks
… fake image detectors also face machine learning attacks that could compromise their effectiveness in filtering out fake images. In this work, we focus on defending the data poisoning attacks on DNN-based fake image detectors in which attackers attempt to fool the fake image detectors by …
-
Defeat data poisoning attacks on facial recognition applications
… passwords. However, the growing number of attacks targeting machine learning, especially Deep Neural Networks (DNN), which is commonly used for facial recognition, imposes big challenges on the successful roll-out of such web-service facial authentication. We demonstrate a new data …
-
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 …
-
DATA POISONING ATTACKS ON PHASOR MEASUREMENT UNIT DATA
… methods are vulnerable against adversarial attacks which potentially can degrade the event classification performance significantly. In this project, we evaluate the vulnerability of event classification models against data poisoning attacks for PMU data using feature collision attack. …
-
Detecting targeted data poisoning attacks on deep neural networks
… 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 behavior. In the context of facial authentication, this could correspond to unauthorized users gaining …
-
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 …
-
PREVENTING DATA POISONING ATTACKS IN FEDERATED MACHINE LEARNING BY AN ENCRYPTED VERIFICATION KEY
… are the attacker and would not use polluted data. This vulnerability enables attackers to train their models using polluted data and then send the polluted updates to the training server for aggregation, potentially poisoning the overall model. In such a setting, it is challenging for an edge …
-
Improving Detection Capabilities of Traditional Machine Learning (ML) Algorithms Against Data Poisoning Attacks on Image Data
… vulnerable to adversarial threats, particularly poisoning attacks that manipulate training data without the knowledge of the ML developers. As ML models are often trained on publicly available data, data poisoning is trivial for attackers to perform, with no way to determine if training data is …
-
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 …
-
Challenges in Large-Scale Machine Learning Systems: Security and Correctness
In this research, we address the impact of data integrity on machine learning algorithms. We study how an adversary could corrupt Bayesian network structure learning algorithms by inserting contaminated data items. We investigate the resilience of two commonly used Bayesian network structure …
-
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 …
-
Deep Neural Network for Anomaly Detection
… (CPSs) services create new surfaces for cyberattacks. To safeguard these CPSs, anomaly detection (AD) that detects potential attacks/adversarial behaviors plays a pivotal role. This thesis aims to design novel deep neural models to handle four challenges of the AD problem to deal with …
-
Un-fair trojan: Targeted backdoor attacks against model fairness
… to be vulnerable against various backdoor and data poisoning attacks that adversely affect model behavior. Additionally, these attacks have been shown to make unfair predictions with respect to certain protected features. In federated learning, multiple local models contribute to a single …
-
Towards Privacy-Preserving and Secure Crowd Sensing in the Internet of Things
… and many others. However, the sensory data provided by the participating users are usually not reliable, due to various reasons such as poor sensor quality, incomplete observations, and background noise. To identify truthful values from the crowd sensing data, a lot of reliability-aware …
-
A Theoretical Investigation Into Adversarially Robust Learning
… admit vulnerabilities in the form of adversarial attacks. One such limitation is due to arbitrary adversarial corruption of data at the time of training, commonly referred to as data poisoning. Another vulnerability is due to arbitrary adversarial corruption of data at the time of prediction, …
-
Data Privacy in the Modern Machine Learning Ecosystem
The explosion of data collection and advances in artificial intelligence and machine learning have motivated a robust economy around cloud-based machine learning services. While such services provide opportunities for a broad array of individuals and companies to leverage the power of modern …
-
Decentralized Machine Learning On Blockchain: Developing A Federated Learning Based System
… these methods have problems like security risks, datastorage issues, and high computational demands. Federated Learning (FL), on theother hand, spreads out the ML process. It trains models on local devices and thencombines them centrally. While FL improves computing and customization, it …
-
Investigating and Evaluating Poison Unlearning under Imperfect Detection
… focused on removing the influence of specific data points from trained machine learning models. Early work in this field has primarily focused on privacy-oriented unlearning, often motivated by data protection regulations such as the GDPR. More recently, security-oriented unlearning has emerged …
Page 1 of 3