相关论文: QuerySnout: Automating the Discovery of Attribute …

Deep Neural Networks can be easily fooled by small and imperceptible perturbations. The query-based black-box attack (QBBA) is able to create the perturbations using model output probabilities of image queries requiring no access to the…

As quantum computing platforms increasingly adopt cloud-based execution, users submit quantum circuits to remote compilers and backends, trusting that what they submit is exactly what will be run. This shift introduces new trust assumptions…

Deep neural networks have recently achieved tremendous success in image classification. Recent studies have however shown that they are easily misled into incorrect classification decisions by adversarial examples. Adversaries can even…

Machine learning security has recently become a prominent topic in the natural language processing (NLP) area. The existing black-box adversarial attack suffers prohibitively from the high model querying complexity, resulting in easily…

Differential privacy is the state-of-the-art definition for privacy, guaranteeing that any analysis performed on a sensitive dataset leaks no information about the individuals whose data are contained therein. In this thesis, we develop…

Although federated learning improves privacy of training data by exchanging local gradients or parameters rather than raw data, the adversary still can leverage local gradients and parameters to obtain local training data by launching…

Digital signatures represent a crucial cryptographic asset that must be protected against quantum adversaries. Quantum Digital Signatures (QDS) can offer solutions that are information-theoretically (IT) secure and thus immune to quantum…

Quantum computing requires the optimization of control pulses to achieve high-fidelity quantum gates. We propose a machine learning-based protocol to address the challenges of evaluating gradients and modeling complex system dynamics. By…

Fingerprinting codes are a crucial tool for proving lower bounds in differential privacy. They have been used to prove tight lower bounds for several fundamental questions, especially in the ``low accuracy'' regime. Unlike…

Artificial Intelligence brings innovations into the society. However, bias and unethical exist in many algorithms that make the applications less trustworthy. Threats hunting algorithms based on machine learning have shown great advantage…

Cloud computing is a powerful and popular information technology paradigm that enables data service outsourcing and provides higher-level services with minimal management effort. However, it is still a key challenge to protect data privacy…

Quantum Neural Networks (QNNs) have shown significant value across domains, with well-trained QNNs representing critical intellectual property often deployed via cloud-based QNN-as-a-Service (QNNaaS) platforms. Recent work has examined QNN…

Recent years have witnessed the adoption of differential privacy (DP) in practical database systems like PINQ, FLEX, and PrivateSQL. Such systems allow data analysts to query sensitive data while providing a rigorous and provable privacy…

More and more users and developers are using Issue Tracking Systems (ITSs) to report issues, including bugs, feature requests, enhancement suggestions, etc. Different information, however, is gathered from users when issues are reported on…

We study the security of Probabilistic Data Structures (PDS) for handling Approximate Membership Queries (AMQ); prominent examples of AMQ-PDS are Bloom and Cuckoo filters. AMQ-PDS are increasingly being deployed in environments where…

Empirical auditing has emerged as a means of catching some of the flaws in the implementation of privacy-preserving algorithms. Existing auditing mechanisms, however, are either computationally inefficient requiring multiple runs of the…

In order to prevent eavesdropping and tampering, the network security protocols use a handshake with an asymmetric cipher to establish a session-specific shared key with which further communication is encrypted using a symmetric cipher. The…

This paper develops a comprehensive framework to address three critical trustworthy challenges in federated learning (FL): robustness against Byzantine attacks, fairness, and privacy preservation. To improve the system's defense against…

Auditing algorithms' privacy typically involves simulating a game-based protocol that guesses which of two adjacent datasets was the original input. Traditional approaches require thousands of such simulations, leading to significant…

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where an attacker manipulates a small portion of the training data to implant hidden backdoors into the model. The compromised model behaves normally on clean samples but…