Algorithmic fairness of machine learning (ML) models has raised significant concern in the recent years. Many testing, verification, and bias mitigation techniques have been proposed to identify and reduce fairness issues in ML models. The existing methods are model-centric and designed to detect fairness issues under static settings. However, many ML-enabled systems operate in a dynamic environment where the predictive decisions made by the system impact the environment, which in turn affects future decision-making. Such a self-reinforcing feedback loop can cause fairness violations in the long term, even if the immediate outcomes are fair. In this paper, we propose a simulation-based framework called FairSense to detect and analyze long-term unfairness in ML-enabled systems. Given a fairness requirement, FairSense performs Monte-Carlo simulation to enumerate evolution traces for each system configuration. Then, FairSense performs sensitivity analysis on the space of possible configurations to understand the impact of design options and environmental factors on the long-term fairness of the system. We demonstrate FairSense's potential utility through three real-world case studies: Loan lending, opioids risk scoring, and predictive policing.

Existing legal frameworks on AI rely on training compute thresholds as a proxy to identify potentially-dangerous AI models and trigger increased regulatory attention. In the United States, Section 4.2(a) of Executive Order 14110 instructs the Secretary of Commerce to require extensive reporting from developers of AI models above a certain training compute threshold. In the European Union, Article 51 of the AI Act establishes a presumption that AI models above a certain compute threshold have high impact capabilities and hence pose systemic risk, thus subjecting their developers to several obligations including capability evaluations, reporting, and incident monitoring. In this paper, we examine some enhancement techniques that are capable of decreasing training compute usage while preserving, or even increasing, model capabilities. Since training compute thresholds rely on training compute as a metric and trigger for increased regulatory attention, these capability-enhancing and compute-saving techniques could constitute a legal loophole to existing training compute thresholds. In particular, we concentrate on four illustrative techniques (fine-tuning, model reuse, model expansion, and above compute-optimal inference compute) with the goal of furthering the conversation about their implications on training compute thresholds as a legal mechanism and advancing policy recommendations that could address the relevant legal loopholes.

We present a multifractal artificial terrain generation method that uses the 3D Weierstrass-Mandelbrot function to control roughness. By varying the fractal dimension used in terrain generation across three different values, we generate 60 unique off-road terrains. We use gradient maps to categorize the roughness of each terrain, consisting of low-, semi-, and high-roughness areas. To test how the fractal dimension affects the difficulty of vehicle traversals, we measure the success rates, vertical accelerations, pitch and roll rates, and traversal times of an autonomous ground vehicle traversing 20 randomized straight-line paths in each terrain. As we increase the fractal dimension from 2.3 to 2.45 and from 2.45 to 2.6, we find that the median area of low-roughness terrain decreases 13.8% and 7.16%, the median area of semi-rough terrain increases 11.7% and 5.63%, and the median area of high-roughness terrain increases 1.54% and 3.33%, all respectively. We find that the median success rate of the vehicle decreases 22.5% and 25% as the fractal dimension increases from 2.3 to 2.45 and from 2.45 to 2.6, respectively. Successful traversal results show that the median root-mean-squared vertical accelerations, median root-mean-squared pitch and roll rates, and median traversal times all increase with the fractal dimension.

The digital age, driven by the AI revolution, brings significant opportunities but also conceals security threats, which we refer to as cyber shadows. These threats pose risks at individual, organizational, and societal levels. This paper examines the systemic impact of these cyber threats and proposes a comprehensive cybersecurity strategy that integrates AI-driven solutions, such as Intrusion Detection Systems (IDS), with targeted policy interventions. By combining technological and regulatory measures, we create a multilevel defense capable of addressing both direct threats and indirect negative externalities. We emphasize that the synergy between AI-driven solutions and policy interventions is essential for neutralizing cyber threats and mitigating their negative impact on the digital economy. Finally, we underscore the need for continuous adaptation of these strategies, especially in response to the rapid advancement of autonomous AI-driven attacks, to ensure the creation of secure and resilient digital ecosystems.

This study explores using Natural Language Processing in aviation safety, focusing on machine learning algorithms to enhance safety measures. There are currently May 2024, 34 Scopus results from the keyword search natural language processing and aviation safety. Analyzing these studies allows us to uncover trends in the methodologies, findings and implications of NLP in aviation. Both qualitative and quantitative tools have been used to investigate the current state of literature on NLP for aviation safety. The qualitative analysis summarises the research motivations, objectives, and outcomes, showing how NLP can be utilized to help identify critical safety issues and improve aviation safety. This study also identifies research gaps and suggests areas for future exploration, providing practical recommendations for the aviation industry. We discuss challenges in implementing NLP in aviation safety, such as the need for large, annotated datasets, and the difficulty in interpreting complex models. We propose solutions like active learning for data annotation and explainable AI for model interpretation. Case studies demonstrate the successful application of NLP in improving aviation safety, highlighting its potential to make aviation safer and more efficient.

The rapid advancement of artificial intelligence, particularly with the development of Large Language Models (LLMs) built on the transformer architecture, has redefined the capabilities of natural language processing. These models now exhibit remarkable performance across various language-related tasks, such as text generation, question answering, translation, and summarization, often rivaling human-like comprehension. More intriguingly, LLMs have demonstrated emergent abilities extending beyond their core functions, showing proficiency in tasks like commonsense reasoning, code generation, and arithmetic. This survey paper explores the foundational components, scaling mechanisms, and architectural strategies that drive these capabilities. Emphasizing models like GPT and LLaMA, we analyze the impact of exponential data and computational growth on LLM performance, while also addressing the trade-offs associated with scaling. We also examine LLM applications across sectors, such as healthcare, finance, education, and law, highlighting their adaptability and potential to solve domain-specific challenges. Central to this work are the questions of how LLMs generalize across diverse tasks, exhibit planning, and reasoning abilities, and whether these emergent abilities can be systematically elicited or enhanced. In particular, we provide some insights into the CoT (Chain of Thought) and PoT (Plan of Thought) abilities within LLMs, focusing on how pre-training data influences their emergence. Additionally, we investigate LLM-modulo frameworks that integrate external systems, allowing LLMs to handle complex, dynamic tasks. By analyzing these factors, this paper aims to foster the ongoing discussion on the capabilities and limits of LLMs, promoting their responsible development and application in novel and increasingly complex environments.

As ML models continue to integrate into critical cybersecurity In the modern landscape of cybersecurity, machine learning systems, the ability to exploit these models through (ML) models, especially in areas like image classification, adversarial techniques poses significant threats. A study predicts are increasingly integrated into systems where robustness and that by 2025, 30% of cyberattacks will involve adversarial security are paramount. However, these models are highly machine-learning tactics[16]. Pre-trained models are susceptible to adversarial attacks, where small, crafted perturbations susceptible to perturbations adversarial attacks, which can can lead to incorrect predictions and, in more severe undermine trust in AI systems due to the lack of customized cases, unauthorized access or manipulation of systems[2].

Federated learning (FL) is a decentralized machine learning technique that allows multiple entities to jointly train a model while preserving dataset privacy. However, its distributed nature has raised various security concerns, which have been addressed by increasingly sophisticated defenses. These protections utilize a range of data sources and metrics to, for example, filter out malicious model updates, ensuring that the impact of attacks is minimized or eliminated. This paper explores the feasibility of designing a generic attack method capable of installing backdoors in FL while evading a diverse array of defenses. Specifically, we focus on an attacker strategy called MIGO, which aims to produce model updates that subtly blend with legitimate ones. The resulting effect is a gradual integration of a backdoor into the global model, often ensuring its persistence long after the attack concludes, while generating enough ambiguity to hinder the effectiveness of defenses. MIGO was employed to implant three types of backdoors across five datasets and different model architectures. The results demonstrate the significant threat posed by these backdoors, as MIGO consistently achieved exceptionally high backdoor accuracy (exceeding 90%) while maintaining the utility of the main task. Moreover, MIGO exhibited strong evasion capabilities against ten defenses, including several state-of-the-art methods. When compared to four other attack strategies, MIGO consistently outperformed them across most configurations. Notably, even in extreme scenarios where the attacker controls just 0.1% of the clients, the results indicate that successful backdoor insertion is possible if the attacker can persist for a sufficient number of rounds.

Deep learning (DL) methods, especially those based on physics-driven DL, have become the state-of-the-art for reconstructing sub-sampled magnetic resonance imaging (MRI) data. However, studies have shown that these methods are susceptible to small adversarial input perturbations, or attacks, resulting in major distortions in the output images. Various strategies have been proposed to reduce the effects of these attacks, but they require retraining and may lower reconstruction quality for non-perturbed/clean inputs. In this work, we propose a novel approach for detecting and mitigating adversarial attacks on MRI reconstruction models without any retraining. Our detection strategy is based on the idea of cyclic measurement consistency. The output of the model is mapped to another set of MRI measurements for a different sub-sampling pattern, and this synthesized data is reconstructed with the same model. Intuitively, without an attack, the second reconstruction is expected to be consistent with the first, while with an attack, disruptions are present. Subsequently, this idea is extended to devise a novel objective function, which is minimized within a small ball around the attack input for mitigation. Experimental results show that our method substantially reduces the impact of adversarial perturbations across different datasets, attack types/strengths and PD-DL networks, and qualitatively and quantitatively outperforms conventional mitigation methods that involve retraining.

Following an analysis of existing AI-related exchange-traded funds (ETFs), we reveal the selection criteria for determining which stocks qualify as AI-related are often opaque and rely on vague phrases and subjective judgments. This paper proposes a new, objective, data-driven approach using natural language processing (NLP) techniques to classify AI stocks by analyzing annual 10-K filings from 3,395 NASDAQ-listed firms between 2011 and 2023. This analysis quantifies each company's engagement with AI through binary indicators and weighted AI scores based on the frequency and context of AI-related terms. Using these metrics, we construct four AI stock indices-the Equally Weighted AI Index (AII), the Size-Weighted AI Index (SAII), and two Time-Discounted AI Indices (TAII05 and TAII5X)-offering different perspectives on AI investment. We validate our methodology through an event study on the launch of OpenAI's ChatGPT, demonstrating that companies with higher AI engagement saw significantly greater positive abnormal returns, with analyses supporting the predictive power of our AI measures. Our indices perform on par with or surpass 14 existing AI-themed ETFs and the Nasdaq Composite Index in risk-return profiles, market responsiveness, and overall performance, achieving higher average daily returns and risk-adjusted metrics without increased volatility. These results suggest our NLP-based approach offers a reliable, market-responsive, and cost-effective alternative to existing AI-related ETF products. Our innovative methodology can also guide investors, asset managers, and policymakers in using corporate data to construct other thematic portfolios, contributing to a more transparent, data-driven, and competitive approach.