Related papers: A Dual-Level Cancelable Framework for Palmprint Ve…
This dissertation proposes a framework of user-centered security in Natural Language Processing (NLP), and demonstrates how it can improve the accessibility of related research. Accordingly, it focuses on two security domains within NLP…
In humanitarian and emergency scenarios, the use of biometrics can dramatically improve the efficiency of operations, but it poses risks for the data subjects, which are exacerbated in contexts of vulnerability. To address this, we present…
We build quantum cryptosystems that support publicly-verifiable deletion from standard cryptographic assumptions. We introduce target-collapsing as a weakening of collapsing for hash functions, analogous to how second preimage resistance…
With the growing adoption of privacy-preserving machine learning algorithms, such as Differentially Private Stochastic Gradient Descent (DP-SGD), training or fine-tuning models on private datasets has become increasingly prevalent. This…
Federated learning (FL) aims to protect data privacy by cooperatively learning a model without sharing private data among users. For Federated Learning of Deep Neural Network with billions of model parameters, existing privacy-preserving…
Nowadays, huge amount of documents are increasingly transferred to the remote servers due to the appealing features of cloud computing. On the other hand, privacy and security of the sensitive information in untrusted cloud environment is a…
Privacy concerns in healthcare have gained interest recently via GDPR, with a rising need for privacy-preserving data collection methods that keep personal information hidden in otherwise usable data. Sometimes data needs to be encrypted…
A well-trained DNN model can be regarded as an intellectual property (IP) of the model owner. To date, many DNN IP protection methods have been proposed, but most of them are watermarking based verification methods where model owners can…
Deep learning-based linkage of records across different databases is becoming increasingly useful in data integration and mining applications to discover new insights from multiple sources of data. However, due to privacy and…
The nonparametric variational information bottleneck (NVIB) provides the foundation for nonparametric variational differential privacy (NVDP), a framework for building privacy-preserving language models. However, the learned latent…
Current developments in Enterprise Systems observe a paradigm shift, moving the needle from the backend to the edge sectors of those; by distributing data, decentralizing applications and integrating novel components seamlessly to the…
Biometric data, such as face images, are often associated with sensitive information (e.g medical, financial, personal government records). Hence, a data breach in a system storing such information can have devastating consequences. Deep…
With the increasing use of cloud-based services for training and deploying machine learning models, data privacy has become a major concern. This is particularly important for natural language processing (NLP) models, which often process…
Deep neural networks have played a crucial part in many critical domains, such as autonomous driving, face recognition, and medical diagnosis. However, deep neural networks are facing security threats from backdoor attacks and can be…
AI-powered generative models have significantly expanded the possibilities for editing, manipulating, and creating high-quality images. Particularly, images that falsely appear to originate from trusted sources pose a serious threat,…
We propose a hybrid model of differential privacy that considers a combination of regular and opt-in users who desire the differential privacy guarantees of the local privacy model and the trusted curator model, respectively. We demonstrate…
Deepfake technology poses increasing risks such as privacy invasion and identity theft. To address these threats, we propose WaveGuard, a proactive watermarking framework that enhances robustness and imperceptibility via frequency-domain…
Thousands of vulnerabilities are reported on a monthly basis to security repositories, such as the National Vulnerability Database. Among these vulnerabilities, software misconfiguration is one of the top 10 security risks for web…
With substantial amount of time, resources and human (team) efforts invested to explore and develop successful deep neural networks (DNN), there emerges an urgent need to protect these inventions from being illegally copied, redistributed,…
Backdoor attacks are among the most effective, practical, and stealthy attacks in deep learning. In this paper, we consider a practical scenario where a developer obtains a deep model from a third party and uses it as part of a…