Research Papers

Guidelines for Artificial Intelligence Containment

James Babcock, Janos Kramar, Roman V. Yampolskiy

With almost daily improvements in capabilities of artificial intelligence it is more important than ever to develop safety software for use by the AI research community. Building on our previous work on AI Containment Problem we propose a number of guidelines which should help AI safety researchers to develop reliable sandboxing software for intelligent programs of all levels. Such safety container software will make it possible to study and analyze intelligent artificial agent while maintaining certain level of safety against information leakage, social engineering attacks and cyberattacks from within the container.

TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly Detection

Joseph Fioresi, Ishan Rajendrakumar Dave, Mubarak Shah

Video anomaly detection (VAD) without human monitoring is a complex computer vision task that can have a positive impact on society if implemented successfully. While recent advances have made significant progress in solving this task, most existing approaches overlook a critical real-world concern: privacy. With the increasing popularity of artificial intelligence technologies, it becomes crucial to implement proper AI ethics into their development. Privacy leakage in VAD allows models to pick up and amplify unnecessary biases related to people's personal information, which may lead to undesirable decision making. In this paper, we propose TeD-SPAD, a privacy-aware video anomaly detection framework that destroys visual private information in a self-supervised manner. In particular, we propose the use of a temporally-distinct triplet loss to promote temporally discriminative features, which complements current weakly-supervised VAD methods. Using TeD-SPAD, we achieve a positive trade-off between privacy protection and utility anomaly detection performance on three popular weakly supervised VAD datasets: UCF-Crime, XD-Violence, and ShanghaiTech. Our proposed anonymization model reduces private attribute prediction by 32.25% while only reducing frame-level ROC AUC on the UCF-Crime anomaly detection dataset by 3.69%. Project Page: https://joefioresi718.github.io/TeD-SPAD_webpage/

Given the great threat of adversarial attacks against Deep Neural Networks (DNNs), numerous works have been proposed to boost transferability to attack real-world applications. However, existing attacks often utilize advanced gradient calculation or input transformation but ignore the white-box model. Inspired by the fact that DNNs are over-parameterized for superior performance, we propose diversifying the high-level features (DHF) for more transferable adversarial examples. In particular, DHF perturbs the high-level features by randomly transforming the high-level features and mixing them with the feature of benign samples when calculating the gradient at each iteration. Due to the redundancy of parameters, such transformation does not affect the classification performance but helps identify the invariant features across different models, leading to much better transferability. Empirical evaluations on ImageNet dataset show that DHF could effectively improve the transferability of existing momentum-based attacks. Incorporated into the input transformation-based attacks, DHF generates more transferable adversarial examples and outperforms the baselines with a clear margin when attacking several defense models, showing its generalization to various attacks and high effectiveness for boosting transferability. Code is available at https://github.com/Trustworthy-AI-Group/DHF.

Parkinson's disease (PD), the second most prevalent neurodegenerative disorder worldwide, frequently presents with early-stage speech impairments. Recent advancements in Artificial Intelligence (AI), particularly deep learning (DL), have significantly enhanced PD diagnosis through the analysis of speech data. Nevertheless, the progress of research is restricted by the limited availability of publicly accessible speech-based PD datasets, primarily due to privacy concerns. The goal of this systematic review is to explore the current landscape of speech-based DL approaches for PD classification, based on 33 scientific works published between January 2020 and March 2024. We discuss their available resources, capabilities, and potential limitations, and issues related to bias, explainability, and privacy. Furthermore, this review provides an overview of publicly accessible speech-based datasets and open-source material for PD. The DL approaches identified are categorized into end-to-end (E2E) learning, transfer learning (TL), and deep acoustic feature extraction (DAFE). Among E2E approaches, Convolutional Neural Networks (CNNs) are prevalent, though Transformers are increasingly popular. E2E approaches face challenges such as limited data and computational resources, especially with Transformers. TL addresses these issues by providing more robust PD diagnosis and better generalizability across languages. DAFE aims to improve the explainability and interpretability of results by examining the specific effects of deep features on both other DL approaches and more traditional machine learning (ML) methods. However, it often underperforms compared to E2E and TL approaches.

Artificial Intelligence (AI) is one of the disruptive technologies that is shaping the future. It has growing applications for data-driven decisions in major smart city solutions, including transportation, education, healthcare, public governance, and power systems. At the same time, it is gaining popularity in protecting critical cyber infrastructure from cyber threats, attacks, damages, or unauthorized access. However, one of the significant issues of those traditional AI technologies (e.g., deep learning) is that the rapid progress in complexity and sophistication propelled and turned out to be uninterpretable black boxes. On many occasions, it is very challenging to understand the decision and bias to control and trust systems' unexpected or seemingly unpredictable outputs. It is acknowledged that the loss of control over interpretability of decision-making becomes a critical issue for many data-driven automated applications. But how may it affect the system's security and trustworthiness? This chapter conducts a comprehensive study of machine learning applications in cybersecurity to indicate the need for explainability to address this question. While doing that, this chapter first discusses the black-box problems of AI technologies for Cybersecurity applications in smart city-based solutions. Later, considering the new technological paradigm, Explainable Artificial Intelligence (XAI), this chapter discusses the transition from black-box to white-box. This chapter also discusses the transition requirements concerning the interpretability, transparency, understandability, and Explainability of AI-based technologies in applying different autonomous systems in smart cities. Finally, it has presented some commercial XAI platforms that offer explainability over traditional AI technologies before presenting future challenges and opportunities.

The Dark Side of Explanations: Poisoning Recommender Systems with Counterfactual Examples

Ziheng Chen, Fabrizio Silvestri, Jia Wang +2

Deep learning-based recommender systems have become an integral part of several online platforms. However, their black-box nature emphasizes the need for explainable artificial intelligence (XAI) approaches to provide human-understandable reasons why a specific item gets recommended to a given user. One such method is counterfactual explanation (CF). While CFs can be highly beneficial for users and system designers, malicious actors may also exploit these explanations to undermine the system's security. In this work, we propose H-CARS, a novel strategy to poison recommender systems via CFs. Specifically, we first train a logical-reasoning-based surrogate model on training data derived from counterfactual explanations. By reversing the learning process of the recommendation model, we thus develop a proficient greedy algorithm to generate fabricated user profiles and their associated interaction records for the aforementioned surrogate model. Our experiments, which employ a well-known CF generation method and are conducted on two distinct datasets, show that H-CARS yields significant and successful attack performance.

Since the mid-10s, the era of Deep Learning (DL) has continued to this day, bringing forth new superlatives and innovations each year. Nevertheless, the speed with which these innovations translate into real applications lags behind this fast pace. Safety-critical applications, in particular, underlie strict regulatory and ethical requirements which need to be taken care of and are still active areas of debate. eXplainable AI (XAI) and privacy-preserving machine learning (PPML) are both crucial research fields, aiming at mitigating some of the drawbacks of prevailing data-hungry black-box models in DL. Despite brisk research activity in the respective fields, no attention has yet been paid to their interaction. This work is the first to investigate the impact of private learning techniques on generated explanations for DL-based models. In an extensive experimental analysis covering various image and time series datasets from multiple domains, as well as varying privacy techniques, XAI methods, and model architectures, the effects of private training on generated explanations are studied. The findings suggest non-negligible changes in explanations through the introduction of privacy. Apart from reporting individual effects of PPML on XAI, the paper gives clear recommendations for the choice of techniques in real applications. By unveiling the interdependencies of these pivotal technologies, this work is a first step towards overcoming the remaining hurdles for practically applicable AI in safety-critical domains.

This article examines the promising prospects and potential hurdles associated with the development of MentorAI, a conceptual AI-driven mentorship platform for professional growth yet to be actualized. The article explores the essential characteristics and technological underpinnings required for the successful creation and efficacy of the MentorAI platform in providing tailored mentorship experiences. The article highlights the transformative potential of MentorAI on various dimensions of professional growth, such as boosting career progression, nurturing skill development, and supporting a balanced work-life environment for professionals. MentorAI, through its AI-based approach, aspires to offer real-time guidance, resources, and assistance customized to each individual's specific needs and goals. Furthermore, the article examines the core technologies crucial to MentorAI's operation, including artificial intelligence, machine learning, and natural language comprehension. These technologies will empower the platform to process user inputs, deliver context-sensitive responses, and dynamically adjust to user preferences and objectives. The deployment of MentorAI presents potential challenges and ethical concerns, as with any groundbreaking technology. The article outlines critical issues like data protection, security, algorithmic bias, and moral quandaries concerning substituting human mentors with AI systems. Addressing these challenges proactively and deliberately is vital to ensure a positive impact on users.

This study explores the complexities of integrating Artificial Intelligence (AI) into Autonomous Vehicles (AVs), examining the challenges introduced by AI components and the impact on testing procedures, focusing on some of the essential requirements for trustworthy AI. Topics addressed include the role of AI at various operational layers of AVs, the implications of the EU's AI Act on AVs, and the need for new testing methodologies for Advanced Driver Assistance Systems (ADAS) and Automated Driving Systems (ADS). The study also provides a detailed analysis on the importance of cybersecurity audits, the need for explainability in AI decision-making processes and protocols for assessing the robustness and ethical behaviour of predictive systems in AVs. The paper identifies significant challenges and suggests future directions for research and development of AI in AV technology, highlighting the need for multidisciplinary expertise.

Society's increasing dependence on Artificial Intelligence (AI) and AI-enabled systems require a more practical approach from software engineering (SE) executives in middle and higher-level management to improve their involvement in implementing AI ethics by making ethical requirements part of their management practices. However, research indicates that most work on implementing ethical requirements in SE management primarily focuses on technical development, with scarce findings for middle and higher-level management. We investigate this by interviewing ten Finnish SE executives in middle and higher-level management to examine how they consider and implement ethical requirements. We use ethical requirements from the European Union (EU) Trustworthy Ethics guidelines for Trustworthy AI as our reference for ethical requirements and an Agile portfolio management framework to analyze implementation. Our findings reveal a general consideration of privacy and data governance ethical requirements as legal requirements with no other consideration for ethical requirements identified. The findings also show practicable consideration of ethical requirements as technical robustness and safety for implementation as risk requirements and societal and environmental well-being for implementation as sustainability requirements. We examine a practical approach to implementing ethical requirements using the ethical risk requirements stack employing the Agile portfolio management framework.

The right to be forgotten (RTBF) is motivated by the desire of people not to be perpetually disadvantaged by their past deeds. For this, data deletion needs to be deep and permanent, and should be removed from machine learning models. Researchers have proposed machine unlearning algorithms which aim to erase specific data from trained models more efficiently. However, these methods modify how data is fed into the model and how training is done, which may subsequently compromise AI ethics from the fairness perspective. To help software engineers make responsible decisions when adopting these unlearning methods, we present the first study on machine unlearning methods to reveal their fairness implications. We designed and conducted experiments on two typical machine unlearning methods (SISA and AmnesiacML) along with a retraining method (ORTR) as baseline using three fairness datasets under three different deletion strategies. Experimental results show that under non-uniform data deletion, SISA leads to better fairness compared with ORTR and AmnesiacML, while initial training and uniform data deletion do not necessarily affect the fairness of all three methods. These findings have exposed an important research problem in software engineering, and can help practitioners better understand the potential trade-offs on fairness when considering solutions for RTBF.

Mimetic Models: Ethical Implications of AI that Acts Like You

Reid McIlroy-Young, Jon Kleinberg, Siddhartha Sen +2

An emerging theme in artificial intelligence research is the creation of models to simulate the decisions and behavior of specific people, in domains including game-playing, text generation, and artistic expression. These models go beyond earlier approaches in the way they are tailored to individuals, and the way they are designed for interaction rather than simply the reproduction of fixed, pre-computed behaviors. We refer to these as mimetic models, and in this paper we develop a framework for characterizing the ethical and social issues raised by their growing availability. Our framework includes a number of distinct scenarios for the use of such models, and considers the impacts on a range of different participants, including the target being modeled, the operator who deploys the model, and the entities that interact with it.