Related papers: Dynamic Robustness Verification Against Weak Memor…

The robustness of a deep classifier can be characterized by its margins: the decision boundary's distances to natural data points. However, it is unclear whether existing robust training methods effectively increase the margin for each…

The growing cybersecurity threats make it essential to use high-quality data to train Machine Learning (ML) models for network traffic analysis, without noisy or missing data. By selecting the most relevant features for cyber-attack…

Features in machine learning problems are often time-varying and may be related to outputs in an algebraic or dynamical manner. The dynamic nature of these machine learning problems renders current higher order accelerated gradient descent…

This paper presents a practical solution for detecting data races in parallel programs. The solution consists of a combination of execution replay (RecPlay) with automatic on-the-fly data race detection. This combination enables us to…

We investigate the problem of runtime analysis of C11 programs under Multi-Copy-Atomic semantics (MCA). Under MCA, one can analyze program outcomes solely through interleaving and reordering of thread events. As a result, obtaining…

We explore the concept of co-design in the context of neural network verification. Specifically, we aim to train deep neural networks that not only are robust to adversarial perturbations but also whose robustness can be verified more…

Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to adversarial attacks, which have brought great concerns when…

The application of reinforcement learning to safety-critical systems is limited by the lack of formal methods for verifying the robustness and safety of learned policies. This paper introduces a novel framework that addresses this gap by…

Transactional access to databases is an important abstraction allowing programmers to consider blocks of actions (transactions) as executing in isolation. The strongest consistency model is {\em serializability}, which ensures the atomicity…

Deep neural networks are vulnerable to adversarial examples, which becomes one of the most important research problems in the development of deep learning. While a lot of efforts have been made in recent years, it is of great significance…

With the popularity and development of the wearable devices such as smartphones, human activity recognition (HAR) based on sensors has become as a key research area in human computer interaction and ubiquitous computing. The emergence of…

Recently a category of tracking methods based on "tracking-by-detection" is widely used in visual tracking problem. Most of these methods update the classifier online using the samples generated by the tracker to handle the appearance…

Among the different possible strategies for evaluating the reliability of individual predictions of classifiers, robustness quantification stands out as a method that evaluates how much uncertainty a classifier could cope with before…

In contrast to electronic computation, chemical computation is noisy and susceptible to a variety of sources of error, which has prevented the construction of robust complex systems. To be effective, chemical algorithms must be designed…

We present algorithms for checking and enforcing robustness of concurrent programs against the Total Store Ordering (TSO) memory model. A program is robust if all its TSO computations correspond to computations under the Sequential…

A vast literature shows that the learning-based visual perception model is sensitive to adversarial noises, but few works consider the robustness of robotic perception models under widely-existing camera motion perturbations. To this end,…

Defect detection is a critical research area in artificial intelligence. Recently, synthetic data-based self-supervised learning has shown great potential on this task. Although many sophisticated synthesizing strategies exist, little…

Deep neural networks (DNNs) are increasingly used in real-world applications (e.g. facial recognition). This has resulted in concerns about the fairness of decisions made by these models. Various notions and measures of fairness have been…

This paper addresses the problem of provably efficient and practically good on-the-fly determinacy race detection in task parallel programs that use futures. Prior works determinacy race detection have mostly focused on either task parallel…

Robust anomaly detection is a requirement for monitoring complex modern systems with applications such as cyber-security, fraud prevention, and maintenance. These systems generate multiple correlated time series that are highly seasonal and…