Related papers: Privacy Leakages in Approximate Adders
We consider an edge computing scenario where users want to perform a linear computation on local, private data and a network-wide, public matrix. Users offload computations to edge servers located at the edge of the network, but do not want…
Alternating direction method of multiplier (ADMM) is a powerful method to solve decentralized convex optimization problems. In distributed settings, each node performs computation with its local data and the local results are exchanged…
Label differential privacy (DP) is a framework that protects the privacy of labels in training datasets, while the feature vectors are public. Existing approaches protect the privacy of labels by flipping them randomly, and then train a…
Major advancements in building general-purpose and customized hardware have been one of the key enablers of versatility and pervasiveness of machine learning models such as deep neural networks. To sustain this ubiquitous deployment of…
The privacy loss distribution (PLD) provides a tight characterization of the privacy loss of a mechanism in the context of differential privacy (DP). Recent work has shown that PLD-based accounting allows for tighter $(\varepsilon,…
Private Information Retrieval (PIR), despite being well studied, is computationally costly and arduous to scale. We explore lower-cost relaxations of information-theoretic PIR, based on dummy queries, sparse vectors, and compositions with…
In this thesis we consider the problem of information hiding in the scenarios of interactive systems, statistical disclosure control, and refinement of specifications. We apply quantitative approaches to information flow in the first two…
Quantum autoencoders allow for reducing the amount of resources in a quantum computation by mapping the original Hilbert space onto a reduced space with the relevant information. Recently, it was proposed to employ approximate quantum…
As power consumption from AI training and inference continues to increase, AI accelerators are being integrated directly into the CPU. Intel's Advanced Matrix Extensions (AMX) is one such example, debuting on the 4th generation Intel Xeon…
Presentation Attack Detection (PAD) systems are usually designed independently of the fingerprint verification system. While this can be acceptable for use cases where specific user templates are not predetermined, it represents a missed…
Recent advances in computing have allowed for the possibility to collect large amounts of data on personal activities and private living spaces. To address the privacy concerns of users in this environment, we propose a novel framework…
Retrieval-Augmented Generation (RAG) enhances the factual accuracy of large language models (LLMs) by conditioning outputs on external knowledge sources. However, when retrieval involves private or sensitive data, RAG systems are…
Distributed computing frameworks such as MapReduce have become essential for large-scale data processing by decomposing tasks across multiple nodes. The multi-access distributed computing (MADC) model further advances this paradigm by…
This study critically examines the methodological rigor in credit card fraud detection research, revealing how fundamental evaluation flaws can overshadow algorithmic sophistication. Through deliberate experimentation with improper…
Many existing Artificial Intelligence (AI) solutions on mobile devices rely on an extensive collection of sensitive data, raising privacy concerns and often requiring storage for both context and model improvement. Apple's Private Cloud…
The rapid integration of AI-powered coding assistants into developer workflows has raised significant privacy and trust concerns. As developers entrust proprietary code to services like OpenAI's GPT, Google's Gemini, and GitHub Copilot, the…
Federated knowledge discovery and data mining are challenged to assess the trustworthiness of data originating from autonomous sources while protecting confidentiality and privacy. Truth-finding algorithms help corroborate data from…
We study the practical effectiveness of privacy amplification for classical key-distribution schemes. We find that in contrast to quantum key distribution schemes, the high fidelity of the raw key generated in classical systems allow the…
Privacy amplification is an indispensable step in postprocessing of continuous-variable quantum key distribution (CV-QKD), which is used to distill unconditional secure keys from identical corrected keys between two distant legal parties.…
In many practical applications of differential privacy, practitioners seek to provide the best privacy guarantees subject to a target level of accuracy. A recent line of work by Ligett et al. '17 and Whitehouse et al. '22 has developed such…