Related papers: Tight Characterizations for Preprocessing against …
Traditional cryptographic techniques, including token obfuscation, are increasingly vulnerable to quantum attacks due to advancements in quantum computing. Quantum algorithms such as Shor's and Grover's pose significant threats to classical…
In this paper, we present "Graph Feature Preprocessor", a software library for detecting typical money laundering patterns in financial transaction graphs in real time. These patterns are used to produce a rich set of transaction features…
Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…
Property-preserving hash functions allow for compressing long inputs $x_0$ and $x_1$ into short hashes $h(x_0)$ and $h(x_1)$ in a manner that allows for computing a predicate $P(x_0, x_1)$ given only the two hash values without having…
In multiple domains such as malware detection, automated driving systems, or fraud detection, classification algorithms are susceptible to being attacked by malicious agents willing to perturb the value of instance covariates to pursue…
Despite their ever more widespread deployment throughout society, machine learning algorithms remain critically vulnerable to being spoofed by subtle adversarial tampering with their input data. The prospect of near-term quantum computers…
Recent studies have verified that semi-supervised learning (SSL) is vulnerable to data poisoning backdoor attacks. Even a tiny fraction of contaminated training data is sufficient for adversaries to manipulate up to 90\% of the test outputs…
Algorithmic fairness has attracted significant attention in recent years, with many quantitative measures suggested for characterizing the fairness of different machine learning algorithms. Despite this interest, the robustness of those…
The following submission constitutes a guide and an introduction to a collection of articles submitted as a Ph.D. dissertation at the University of Gda\'nsk. In the dissertation, we study the fundamental limitations within the selected…
Security of a storage device against a tampering adversary has been a well-studied topic in classical cryptography. Such models give black-box access to an adversary, and the aim is to protect the stored message or abort the protocol if…
Quantum computational advantage refers to an existence of computational tasks that are easy for quantum computing but hard for classical one. Unconditionally showing quantum advantage is beyond our current understanding of complexity…
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…
Machine learning models have been widely adopted in several fields. However, most recent studies have shown several vulnerabilities from attacks with a potential to jeopardize the integrity of the model, presenting a new window of research…
Computational indistinguishability is a key property in cryptography and verification of security protocols. Current tools for proving it rely on cryptographic game transformations. We follow Bana and Comon's approach, axiomatizing what an…
The gaming industry has experienced substantial growth, but cheating in online games poses a significant threat to the integrity of the gaming experience. Cheating, particularly in first-person shooter (FPS) games, can lead to substantial…
Phishing is an online identity theft that aims to steal sensitive information such as username, password and online banking details from its victims. Phishing education needs to be considered as a means to combat this threat. This paper…
The increasing scale and sophistication of cyberattacks has led to the adoption of machine learning based classification techniques, at the core of cybersecurity systems. These techniques promise scale and accuracy, which traditional rule…
Minimizing risk with fairness constraints is one of the popular approaches to learning a fair classifier. Recent works showed that this approach yields an unfair classifier if the training set is corrupted. In this work, we study the…
Considering the premise that the number of products offered grow in an exponential fashion and the amount of data that a user can assimilate before making a decision is relatively small, recommender systems help in categorizing content…
We give a natural problem over input quantum oracles $U$ which cannot be solved with exponentially many black-box queries to $U$ and $U^\dagger$, but which can be solved with constant many queries to $U$ and $U^*$, or $U$ and…