ACM Computing Surveys

Artificial intelligence (AI) is a very powerful technology and can be a potential disrupter and essential enabler. As AI expands into almost every aspect of our lives, people raise serious concerns about AI misbehaving and misuse. To address this concern, ...

Humans working with autonomous artificially intelligent systems may not be experts in the inner workings of their machine teammates, but need to understand when to employ, trust, and rely on the system. A critical challenge is to develop machine agents ...

Data quality is a key factor in the development of trustworthy AI in healthcare. A large volume of curated datasets with controlled confounding factors can improve the accuracy, robustness, and privacy of downstream AI algorithms. However, access to high-...

When Machine Learning technologies are used in contexts that affect citizens, companies as well as researchers need to be confident that there will not be any unexpected social implications, such as bias towards gender, ethnicity, and/or people with ...

Machine Learning solutions have spread along many domains, including critical applications. The development of such models usually relies on a dataset containing labeled data. This dataset is then split into training and test sets and the accuracy of the ...

Explainable reinforcement learning (XRL) is an emerging subfield of explainable machine learning that has attracted considerable attention in recent years. The goal of XRL is to elucidate the decision-making process of reinforcement learning (RL) agents ...

The problem of Byzantine resilience in distributed machine learning, a.k.a. Byzantine machine learning, consists of designing distributed algorithms that can train an accurate model despite the presence of Byzantine nodes—that is, nodes with corrupt data ...

Metaverse is expected to emerge as a new paradigm for the next-generation Internet, providing fully immersive and personalized experiences to socialize, work, and play in self-sustaining and hyper-spatio-temporal virtual world(s). The advancements in ...

Graph Neural Networks (GNNs) perform well in community detection and molecule classification. Counterfactual Explanations (CE) provide counter-examples to overcome the transparency limitations of black-box models. Due to the growing attention in graph ...

Large-scale datasets have played a crucial role in the advancement of computer vision. However, they often suffer from problems such as class imbalance, noisy labels, dataset bias, or high resource costs, which can inhibit model performance and reduce ...

Responsible Artificial Intelligence (RAI) is widely considered as one of the greatest scientific challenges of our time and is key to increase the adoption of Artificial Intelligence (AI). Recently, a number of AI ethics principles frameworks have been ...

Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to confuse the model into making a mistake. Such examples pose a serious threat to the applicability of machine learning-based systems, especially in ...

Data Poisoning Attacks (DPA) represent a sophisticated technique aimed at distorting the training data of machine learning models, thereby manipulating their behavior. This process is not only technically intricate but also frequently dependent on the ...

Artificial Intelligence (AI) can enable the development of next-generation autonomous safety-critical systems in which Machine Learning (ML) algorithms learn optimized and safe solutions. AI can also support and assist human safety engineers in developing ...

Traditional methods for sentiment analysis, when applied in a monolingual context, often yield less than optimal results in multilingual settings. This underscores the need for a more thorough exploration of cross-lingual sentiment analysis (CLSA) ...

Microarchitectural vulnerabilities, such as Meltdown and Spectre, exploit subtle microarchitecture state to steal the user’s secret data and even compromise the operating systems. In recent years, considerable discussion lies in understanding the attack-...

Blockchain offers immutability, transparency, and security in a decentralised way for many applications, including finance, supply chain, and the Internet of Things (IoT). Due to its popularity and widespread adoption, it has started to process an ...

Reversible data hiding (RDH) has developed various theories and algorithms since the early 1990s. The existing works involve a large amount of specialized knowledge, making it difficult for researchers, especially primary learners, to have a good ...

Cameras in modern devices such as smartphones, satellites and medical equipment are capable of capturing very high resolution images and videos. Such high-resolution data often need to be processed by deep learning models for cancer detection, automated ...

Online Social Networks (OSNs) are becoming pervasive in today’s world. Millions of people worldwide are involved in different forms of online networking. However, this ease of use of OSNs comes with a cost in terms of privacy. Users of OSNs become victims ...

Over the past decade, wearable activity trackers (WATs) have become increasingly popular. However, despite many research studies in different fields (e.g. psychology, health, and design), few have sought to jointly examine the critical aspects of utility (...

This article surveys the Variable Autonomy (VA) robotics literature that considers two contributory elements to Trustworthy AI: transparency and explainability. These elements should play a crucial role when designing and adopting robotic systems, ...

Recent years have witnessed a substantial increase in the use of deep learning to solve various natural language processing (NLP) problems. Early deep learning models were constrained by their sequential or unidirectional nature, such that they struggled ...

Authentication and Session Key Generation Protocols (SKGPs) play an essential role in securing the communication channels of connected Internet of Things (IoT) devices. Recently, through blockchain integration, scholars have tried to enhance the security ...

Multi-view clustering (MVC) holds a significant role in domains like machine learning, data mining, and pattern recognition. Despite the development of numerous new MVC approaches employing various techniques, there remains a gap in comprehensive studies ...

As the societal impact of Deep Neural Networks (DNNs) grows, the goals for advancing DNNs become more complex and diverse, ranging from improving a conventional model accuracy metric to infusing advanced human virtues such as fairness, accountability, ...

Video Anomaly Detection (VAD) serves as a pivotal technology in the intelligent surveillance systems, enabling the temporal or spatial identification of anomalous events within videos. While existing reviews predominantly concentrate on conventional ...

Wearable devices, or wearables, designed to be attached to the human body, can gather personalized real-time data and continuously monitor an individual’s health status and physiological disposition in a non-invasive manner. Intelligent wearables ...