Related papers: On Algorithms verifying Initial-and-Final-State Op…
In this work we investigate the problem of simultaneous privacy and integrity protection in cryptographic circuits. We consider a white-box scenario with a powerful, yet limited attacker. A concise metric for the level of probing and fault…
Machine learning models in safety-critical settings like healthcare are often blackboxes: they contain a large number of parameters which are not transparent to users. Post-hoc explainability methods where a simple, human-interpretable…
It is known that big data analytics and AI pose a threat to privacy, and that some of this is due to some kind of "black box problem" in AI. I explain how this becomes a problem in the context of justification for judgments and actions.…
A connection between the state estimation problem and the separability problem is noticed and exploited to find efficient numerical algorithms to solve the first one. Based on these ideas, we also derive a systematic method to obtain upper…
The intersection of artificial intelligence (AI) and digital forensics (DF) is becoming increasingly complex, ubiquitous, and pervasive, with overlapping techniques and technologies being adopted in all types of scientific and technical…
This paper proposes a novel global optimization algorithm, Particle Filter-Based Optimization (PFO), designed for a class of stochastic optimization problems in which the objective function lacks an analytical form and is subject to noisy…
The operator fidelity is a measure of the information-theoretic distinguishability between perturbed and unperturbed evolutions. The response of this measure to the perturbation may be formulated in terms of the operator fidelity…
Transactional memory is a mechanism that manages thread synchronisation on behalf of a programmer so that blocks of code execute with an illusion of atomicity. The main safety criterion for transactional memory is opacity, which defines…
Fairness in machine learning is more important than ever as ethical concerns continue to grow. Individual fairness demands that individuals differing only in sensitive attributes receive the same outcomes. However, commonly used machine…
Detecting when a neural sequence model does "interesting" computation is an open problem. The next token prediction loss is a poor indicator: Low loss can stem from trivially predictable sequences that are uninteresting, while high loss may…
In today's age of internet and social media, one can find an enormous volume of forged images on-line. These images have been used in the past to convey falsified information and achieve harmful intentions. The spread and the effect of the…
Observational determinism is a security property that characterizes secure information flow for multithreaded programs. Most of the methods that have been used to verify observational determinism are based on either type systems or…
Many quantum systems exhibit high sensitivity to their initial conditions, where microscopic quantum fluctuations can significantly influence macroscopic observables. Understanding how quantum states may influence the behavior of nonlinear…
Dehazing is in the image processing and computer vision communities, the task of enhancing the image taken in foggy conditions. To better understand this type of algorithm, we present in this document a dehazing method which is suitable for…
Entanglement and coherence are fundamental properties of quantum systems, promising to power near future quantum technologies, such as quantum computation, quantum communication and quantum metrology. Yet, their quantification, rather than…
We focus on determining the separability of an unknown bipartite quantum state $\rho$ by invoking a sufficiently large subset of all possible entanglement witnesses given the expected value of each element of a set of mutually orthogonal…
Vision, as an inexpensive yet information rich sensor, is commonly used for perception on autonomous mobile robots. Unfortunately, accurate vision-based perception requires a number of assumptions about the environment to hold -- some…
Privacy becomes a crucial issue when outsourcing the training of machine learning (ML) models to cloud-based platforms offering machine-learning services. While solutions based on cryptographic primitives have been developed, they incur a…
In contrast to entropy, which increases monotonically, the "complexity" or "interestingness" of closed systems seems intuitively to increase at first and then decrease as equilibrium is approached. For example, our universe lacked complex…
Formal modeling of cyber-physical systems (CPS) is hard, because they pose the double challenge of combined discrete-continuous dynamics and concurrent behavior. Existing formal specification and verification languages for CPS are designed…