Research Papers

With the rise of Internet of Things (IoT) technologies in smart homes and the integration of artificial intelligence (AI), ethical concerns have become increasingly significant. This paper explores the ethical implications of AI-driven detection technologies in smart homes using the User Requirements Notation (URN) framework. In this paper, we thoroughly conduct thousands of related works from 1985 to 2024 to identify key trends in AI ethics, algorithm methods, and technological advancements. The study presents an overview of smart home and AI ethics, comparing traditional and AI-specific ethical issues, and provides guidelines for ethical design across areas like privacy, fairness, transparency, accountability, and user autonomy, offering insights for developers and researchers in smart homes.

The REAIM 2024 Blueprint for Action states that AI applications in the military domain should be ethical and human-centric and that humans must remain responsible and accountable for their use and effects. Developing rigorous test and evaluation, verification and validation (TEVV) frameworks will contribute to robust oversight mechanisms. TEVV in the development and deployment of AI systems needs to involve human users throughout the lifecycle. Traditional human-centred test and evaluation methods from human factors need to be adapted for deployed AI systems that require ongoing monitoring and evaluation. The language around AI-enabled systems should be shifted to inclusion of the human(s) as a component of the system. Standards and requirements supporting this adjusted definition are needed, as are metrics and means to evaluate them. The need for dialogue between technologists and policymakers on human-centred TEVV will be evergreen, but dialogue needs to be initiated with an objective in mind for it to be productive. Development of TEVV throughout system lifecycle is critical to support this evolution including the issue of human scalability and impact on scale of achievable testing. Communication between technical and non technical communities must be improved to ensure operators and policy-makers understand risk assumed by system use and to better inform research and development. Test and evaluation in support of responsible AI deployment must include the effect of the human to reflect operationally realised system performance. Means of communicating the results of TEVV to those using and making decisions regarding the use of AI based systems will be key in informing risk based decisions regarding use.

Explainable Artificial Intelligence (XAI) emerged to reveal the internal mechanism of machine learning models and how the features affect the prediction outcome. Collinearity is one of the big issues that XAI methods face when identifying the most informative features in the model. Current XAI approaches assume the features in the models are independent and calculate the effect of each feature toward model prediction independently from the rest of the features. However, such assumption is not realistic in real life applications. We propose an Additive Effects of Collinearity (AEC) as a novel XAI method that aim to considers the collinearity issue when it models the effect of each feature in the model on the outcome. AEC is based on the idea of dividing multivariate models into several univariate models in order to examine their impact on each other and consequently on the outcome. The proposed method is implemented using simulated and real data to validate its efficiency comparing with the a state of arts XAI method. The results indicate that AEC is more robust and stable against the impact of collinearity when it explains AI models compared with the state of arts XAI method.

A Methodology for Incompleteness-Tolerant and Modular Gradual Semantics for Argumentative Statement Graphs

Antonio Rago, Stylianos Loukas Vasileiou, Francesca Toni +2

Gradual semantics (GS) have demonstrated great potential in argumentation, in particular for deploying quantitative bipolar argumentation frameworks (QBAFs) in a number of real-world settings, from judgmental forecasting to explainable AI. In this paper, we provide a novel methodology for obtaining GS for statement graphs, a form of structured argumentation framework, where arguments and relations between them are built from logical statements. Our methodology differs from existing approaches in the literature in two main ways. First, it naturally accommodates incomplete information, so that arguments with partially specified premises can play a meaningful role in the evaluation. Second, it is modularly defined to leverage on any GS for QBAFs. We also define a set of novel properties for our GS and study their suitability alongside a set of existing properties (adapted to our setting) for two instantiations of our GS, demonstrating their advantages over existing approaches.

Countering Autonomous Cyber Threats

Kade M. Heckel, Adrian Weller

With the capability to write convincing and fluent natural language and generate code, Foundation Models present dual-use concerns broadly and within the cyber domain specifically. Generative AI has already begun to impact cyberspace through a broad illicit marketplace for assisting malware development and social engineering attacks through hundreds of malicious-AI-as-a-services tools. More alarming is that recent research has shown the potential for these advanced models to inform or independently execute offensive cyberspace operations. However, these previous investigations primarily focused on the threats posed by proprietary models due to the until recent lack of strong open-weight model and additionally leave the impacts of network defenses or potential countermeasures unexplored. Critically, understanding the aptitude of downloadable models to function as offensive cyber agents is vital given that they are far more difficult to govern and prevent their misuse. As such, this work evaluates several state-of-the-art FMs on their ability to compromise machines in an isolated network and investigates defensive mechanisms to defeat such AI-powered attacks. Using target machines from a commercial provider, the most recently released downloadable models are found to be on par with a leading proprietary model at conducting simple cyber attacks with common hacking tools against known vulnerabilities. To mitigate such LLM-powered threats, defensive prompt injection (DPI) payloads for disrupting the malicious cyber agent's workflow are demonstrated to be effective. From these results, the implications for AI safety and governance with respect to cybersecurity is analyzed.

eXplainable Artificial Intelligence (XAI) has garnered significant attention for enhancing transparency and trust in machine learning models. However, the scopes of most existing explanation techniques focus either on offering a holistic view of the explainee model (global explanation) or on individual instances (local explanation), while the middle ground, i.e., cohort-based explanation, is less explored. Cohort explanations offer insights into the explainee's behavior on a specific group or cohort of instances, enabling a deeper understanding of model decisions within a defined context. In this paper, we discuss the unique challenges and opportunities associated with measuring cohort explanations, define their desired properties, and create a generalized framework for generating cohort explanations based on supervised clustering.

In November 2023, the UK and US announced the creation of their AI Safety Institutes (AISIs). Five other jurisdictions have followed in establishing AISIs or similar institutions, with more likely to follow. While there is considerable variation between these institutions, there are also key similarities worth identifying. This primer describes one cluster of similar AISIs, the "first wave," consisting of the Japan, UK, and US AISIs. First-wave AISIs have several fundamental characteristics in common: they are technical government institutions, have a clear mandate related to the safety of advanced AI systems, and lack regulatory powers. Safety evaluations are at the center of first-wave AISIs. These techniques test AI systems across tasks to understand their behavior and capabilities on relevant risks, such as cyber, chemical, and biological misuse. They also share three core functions: research, standards, and cooperation. These functions are critical to AISIs' work on safety evaluations but also support other activities such as scientific consensus-building and foundational AI safety research. Despite its growing popularity as an institutional model, the AISI model is not free from challenges and limitations. Some analysts have criticized the first wave of AISIs for specializing too much in a sub-area and for being potentially redundant with existing institutions, for example. Future developments may rapidly change this landscape, and particularities of individual AISIs may not be captured by our broad-strokes description. This policy brief aims to outline the core elements of first-wave AISIs as a way of encouraging and improving conversations on this novel institutional model, acknowledging this is just a simplified snapshot rather than a timeless prescription.

Natural Language Counterfactual Explanations for Graphs Using Large Language Models

Flavio Giorgi, Cesare Campagnano, Fabrizio Silvestri +1

Explainable Artificial Intelligence (XAI) has emerged as a critical area of research to unravel the opaque inner logic of (deep) machine learning models. Among the various XAI techniques proposed in the literature, counterfactual explanations stand out as one of the most promising approaches. However, these "what-if" explanations are frequently complex and technical, making them difficult for non-experts to understand and, more broadly, challenging for humans to interpret. To bridge this gap, in this work, we exploit the power of open-source Large Language Models to generate natural language explanations when prompted with valid counterfactual instances produced by state-of-the-art explainers for graph-based models. Experiments across several graph datasets and counterfactual explainers show that our approach effectively produces accurate natural language representations of counterfactual instances, as demonstrated by key performance metrics.

Recent high profile incidents in which the use of Large Language Models (LLMs) resulted in significant harm to individuals have brought about a growing interest in AI safety. One reason LLM safety issues occur is that models often have at least some non-zero probability of producing harmful outputs. In this work, we explore the following scenario: imagine an AI safety auditor is searching for catastrophic responses from an LLM (e.g. a "yes" responses to "can I fire an employee for being pregnant?"), and is able to query the model a limited number times (e.g. 1000 times). What is a strategy for querying the model that would efficiently find those failure responses? To this end, we propose output scouting: an approach that aims to generate semantically fluent outputs to a given prompt matching any target probability distribution. We then run experiments using two LLMs and find numerous examples of catastrophic responses. We conclude with a discussion that includes advice for practitioners who are looking to implement LLM auditing for catastrophic responses. We also release an open-source toolkit (https://github.com/joaopfonseca/outputscouting) that implements our auditing framework using the Hugging Face transformers library.

This paper presents a probabilistic approach to analyzing copyright infringement disputes. Evidentiary principles shaped by case law are formalized in probabilistic terms, and the ``inverse ratio rule'' -- a controversial legal doctrine adopted by some courts -- is examined. Although this rule has faced significant criticism, a formal proof demonstrates its validity, provided it is properly defined. The probabilistic approach is further employed to study the copyright safety of generative AI. Specifically, the Near Access-Free (NAF) condition, previously proposed as a strategy for mitigating the heightened copyright infringement risks of generative AI, is evaluated. The analysis reveals limitations in its justifiability and efficacy.

Faithfulness is arguably the most critical metric to assess the reliability of explainable AI. In NLP, current methods for faithfulness evaluation are fraught with discrepancies and biases, often failing to capture the true reasoning of models. We introduce Adversarial Sensitivity as a novel approach to faithfulness evaluation, focusing on the explainer's response when the model is under adversarial attack. Our method accounts for the faithfulness of explainers by capturing sensitivity to adversarial input changes. This work addresses significant limitations in existing evaluation techniques, and furthermore, quantifies faithfulness from a crucial yet underexplored paradigm.

In the field of explainable AI, a vibrant effort is dedicated to the design of self-explainable models, as a more principled alternative to post-hoc methods that attempt to explain the decisions after a model opaquely makes them. However, this productive line of research suffers from common downsides: lack of reproducibility, unfeasible comparison, diverging standards. In this paper, we propose CaBRNet, an open-source, modular, backward-compatible framework for Case-Based Reasoning Networks: https://github.com/aiser-team/cabrnet.