Related papers: Worst-Case Input Generation for Concurrent Program…
We propose the Constraint-Generation Policy Optimization (CGPO) framework to optimize policy parameters within compact and interpretable policy classes for mixed discrete-continuous Markov Decision Processes (DC-MDP). CGPO can not only…
We introduce a novel concept, called Name Confusion, and demonstrate how it can be employed to thwart multiple classes of code-reuse attacks. By building upon Name Confusion, we derive Phantom Name System (PNS): a security protocol that…
Business Process Management (BPM) is gaining increasing attention as it has the potential to cut costs while boosting output and quality. Business process document generation is a crucial stage in BPM. However, due to a shortage of…
Modern end-to-end speech recognition models show astonishing results in transcribing audio signals into written text. However, conventional data feeding pipelines may be sub-optimal for low-resource speech recognition, which still remains a…
Modern processors deploy a variety of weak memory models, which for efficiency reasons may execute instructions in an order different to that specified by the program text. The consequences of instruction reordering can be complex and…
We introduce algorithms that use predictions from machine learning applied to the input to circumvent worst-case analysis. We aim for algorithms that have near optimal performance when these predictions are good, but recover the…
Ensuring timing guarantees for every individual tasks is critical in real-time systems. Even for periodic tasks, providing timing guarantees for tasks with segmented self-suspending behavior is challenging due to timing anomalies, i.e., the…
Advances in deep learning have enabled a wide range of promising applications. However, these systems are vulnerable to Adversarial Machine Learning (AML) attacks; adversarially crafted perturbations to their inputs could cause them to…
Symbolic regression (SR) is the problem of learning a symbolic expression from numerical data. Recently, deep neural models trained on procedurally-generated synthetic datasets showed competitive performance compared to more classical…
We consider a worst-case asymmetric distributed source coding problem where an information sink communicates with $N$ correlated information sources to gather their data. A data-vector $\bar{x} = (x_1, ..., x_N) \sim {\mathcal P}$ is…
This paper presents CAMP, a new static performance analysis framework for message-passing concurrent and distributed systems, based on the theory of multiparty session types (MPST). Understanding the run-time performance of concurrent and…
State of the art (SOTA) neural text to speech (TTS) models can generate natural-sounding synthetic voices. These models are characterized by large memory footprints and substantial number of operations due to the long-standing focus on…
We propose two novel techniques --- stacking bottleneck features and minimum generation error training criterion --- to improve the performance of deep neural network (DNN)-based speech synthesis. The techniques address the related issues…
Effective performance profiling and analysis are essential for optimizing training and inference of deep learning models, especially given the growing complexity of heterogeneous computing environments. However, existing tools often lack…
Program synthesis is an umbrella term for generating programs and logical formulae from specifications. With the remarkable performance improvements that GPUs enable for deep learning, a natural question arose: can we also implement a…
We present an elementary branch and bound algorithm with a simple analysis of why it achieves worstcase optimality for join queries on classes of databases defined respectively by cardinality or acyclic degree constraints. We then show that…
Adversarial robustness evaluates the worst-case performance scenario of a machine learning model to ensure its safety and reliability. This study is the first to investigate the robustness of visually grounded dialog models towards textual…
Standard H-infinity/H2 robust control and analysis tools operate on uncertain parameters assumed to vary independently within prescribed bounds. This paper extends their capabilities in the presence of constraints coupling these parameters…
Recent research shows the susceptibility of machine learning models to adversarial attacks, wherein minor but maliciously chosen perturbations of the input can significantly degrade model performance. In this paper, we theoretically analyse…
Recently, deep learning-based Text-to-Speech (TTS) systems have achieved high-quality speech synthesis results. Recurrent neural networks have become a standard modeling technique for sequential data in TTS systems and are widely used.…