Research Papers

Current machine-learning based software vulnerability detection methods are primarily conducted at the function-level. However, a key limitation of these methods is that they do not indicate the specific lines of code contributing to vulnerabilities. This limits the ability of developers to efficiently inspect and interpret the predictions from a learnt model, which is crucial for integrating machine-learning based tools into the software development workflow. Graph-based models have shown promising performance in function-level vulnerability detection, but their capability for statement-level vulnerability detection has not been extensively explored. While interpreting function-level predictions through explainable AI is one promising direction, we herein consider the statement-level software vulnerability detection task from a fully supervised learning perspective. We propose a novel deep learning framework, LineVD, which formulates statement-level vulnerability detection as a node classification task. LineVD leverages control and data dependencies between statements using graph neural networks, and a transformer-based model to encode the raw source code tokens. In particular, by addressing the conflicting outputs between function-level and statement-level information, LineVD significantly improve the prediction performance without vulnerability status for function code. We have conducted extensive experiments against a large-scale collection of real-world C/C++ vulnerabilities obtained from multiple real-world projects, and demonstrate an increase of 105\% in F1-score over the current state-of-the-art.

Recent technological advances in synthetic data have enabled the generation of images with such high quality that human beings cannot tell the difference between real-life photographs and Artificial Intelligence (AI) generated images. Given the critical necessity of data reliability and authentication, this article proposes to enhance our ability to recognise AI-generated images through computer vision. Initially, a synthetic dataset is generated that mirrors the ten classes of the already available CIFAR-10 dataset with latent diffusion which provides a contrasting set of images for comparison to real photographs. The model is capable of generating complex visual attributes, such as photorealistic reflections in water. The two sets of data present as a binary classification problem with regard to whether the photograph is real or generated by AI. This study then proposes the use of a Convolutional Neural Network (CNN) to classify the images into two categories; Real or Fake. Following hyperparameter tuning and the training of 36 individual network topologies, the optimal approach could correctly classify the images with 92.98% accuracy. Finally, this study implements explainable AI via Gradient Class Activation Mapping to explore which features within the images are useful for classification. Interpretation reveals interesting concepts within the image, in particular, noting that the actual entity itself does not hold useful information for classification; instead, the model focuses on small visual imperfections in the background of the images. The complete dataset engineered for this study, referred to as the CIFAKE dataset, is made publicly available to the research community for future work.

Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning

Seul-Ki Yeom, Philipp Seegerer, Sebastian Lapuschkin +4

The success of convolutional neural networks (CNNs) in various applications is accompanied by a significant increase in computation and parameter storage costs. Recent efforts to reduce these overheads involve pruning and compressing the weights of various layers while at the same time aiming to not sacrifice performance. In this paper, we propose a novel criterion for CNN pruning inspired by neural network interpretability: The most relevant units, i.e. weights or filters, are automatically found using their relevance scores obtained from concepts of explainable AI (XAI). By exploring this idea, we connect the lines of interpretability and model compression research. We show that our proposed method can efficiently prune CNN models in transfer-learning setups in which networks pre-trained on large corpora are adapted to specialized tasks. The method is evaluated on a broad range of computer vision datasets. Notably, our novel criterion is not only competitive or better compared to state-of-the-art pruning criteria when successive retraining is performed, but clearly outperforms these previous criteria in the resource-constrained application scenario in which the data of the task to be transferred to is very scarce and one chooses to refrain from fine-tuning. Our method is able to compress the model iteratively while maintaining or even improving accuracy. At the same time, it has a computational cost in the order of gradient computation and is comparatively simple to apply without the need for tuning hyperparameters for pruning.

Trustworthy AI

Richa Singh, Mayank Vatsa, Nalini Ratha

Modern AI systems are reaping the advantage of novel learning methods. With their increasing usage, we are realizing the limitations and shortfalls of these systems. Brittleness to minor adversarial changes in the input data, ability to explain the decisions, address the bias in their training data, high opacity in terms of revealing the lineage of the system, how they were trained and tested, and under which parameters and conditions they can reliably guarantee a certain level of performance, are some of the most prominent limitations. Ensuring the privacy and security of the data, assigning appropriate credits to data sources, and delivering decent outputs are also required features of an AI system. We propose the tutorial on Trustworthy AI to address six critical issues in enhancing user and public trust in AI systems, namely: (i) bias and fairness, (ii) explainability, (iii) robust mitigation of adversarial attacks, (iv) improved privacy and security in model building, (v) being decent, and (vi) model attribution, including the right level of credit assignment to the data sources, model architectures, and transparency in lineage.

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

Tomek Korbak, Mikita Balesni, Elizabeth Barnes +38

AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known AI oversight methods, CoT monitoring is imperfect and allows some misbehavior to go unnoticed. Nevertheless, it shows promise and we recommend further research into CoT monitorability and investment in CoT monitoring alongside existing safety methods. Because CoT monitorability may be fragile, we recommend that frontier model developers consider the impact of development decisions on CoT monitorability.

Lack of adequate training samples and noisy high-dimensional features are key challenges faced by Motor Imagery (MI) decoding algorithms for electroencephalogram (EEG) based Brain-Computer Interface (BCI). To address these challenges, inspired from neuro-physiological signatures of MI, this paper proposes a novel Filter-Bank Convolutional Network (FBCNet) for MI classification. FBCNet employs a multi-view data representation followed by spatial filtering to extract spectro-spatially discriminative features. This multistage approach enables efficient training of the network even when limited training data is available. More significantly, in FBCNet, we propose a novel Variance layer that effectively aggregates the EEG time-domain information. With this design, we compare FBCNet with state-of-the-art (SOTA) BCI algorithm on four MI datasets: The BCI competition IV dataset 2a (BCIC-IV-2a), the OpenBMI dataset, and two large datasets from chronic stroke patients. The results show that, by achieving 76.20% 4-class classification accuracy, FBCNet sets a new SOTA for BCIC-IV-2a dataset. On the other three datasets, FBCNet yields up to 8% higher binary classification accuracies. Additionally, using explainable AI techniques we present one of the first reports about the differences in discriminative EEG features between healthy subjects and stroke patients. Also, the FBCNet source code is available at https://github.com/ravikiran-mane/FBCNet.

Degenerate Feedback Loops in Recommender Systems

Ray Jiang, Silvia Chiappa, Tor Lattimore +2

Machine learning is used extensively in recommender systems deployed in products. The decisions made by these systems can influence user beliefs and preferences which in turn affect the feedback the learning system receives - thus creating a feedback loop. This phenomenon can give rise to the so-called "echo chambers" or "filter bubbles" that have user and societal implications. In this paper, we provide a novel theoretical analysis that examines both the role of user dynamics and the behavior of recommender systems, disentangling the echo chamber from the filter bubble effect. In addition, we offer practical solutions to slow down system degeneracy. Our study contributes toward understanding and developing solutions to commonly cited issues in the complex temporal scenario, an area that is still largely unexplored.

There has been a growing interest in model-agnostic methods that can make deep learning models more transparent and explainable to a user. Some researchers recently argued that for a machine to achieve a certain degree of human-level explainability, this machine needs to provide human causally understandable explanations, also known as causability. A specific class of algorithms that have the potential to provide causability are counterfactuals. This paper presents an in-depth systematic review of the diverse existing body of literature on counterfactuals and causability for explainable artificial intelligence. We performed an LDA topic modelling analysis under a PRISMA framework to find the most relevant literature articles. This analysis resulted in a novel taxonomy that considers the grounding theories of the surveyed algorithms, together with their underlying properties and applications in real-world data. This research suggests that current model-agnostic counterfactual algorithms for explainable AI are not grounded on a causal theoretical formalism and, consequently, cannot promote causability to a human decision-maker. Our findings suggest that the explanations derived from major algorithms in the literature provide spurious correlations rather than cause/effects relationships, leading to sub-optimal, erroneous or even biased explanations. This paper also advances the literature with new directions and challenges on promoting causability in model-agnostic approaches for explainable artificial intelligence.

Personality Traits in Large Language Models

Greg Serapio-García, Mustafa Safdari, Clément Crepy +6

The advent of large language models (LLMs) has revolutionized natural language processing, enabling the generation of coherent and contextually relevant human-like text. As LLMs increasingly powerconversational agents used by the general public world-wide, the synthetic personality traits embedded in these models, by virtue of training on large amounts of human data, is becoming increasingly important. Since personality is a key factor determining the effectiveness of communication, we present a novel and comprehensive psychometrically valid and reliable methodology for administering and validating personality tests on widely-used LLMs, as well as for shaping personality in the generated text of such LLMs. Applying this method to 18 LLMs, we found: 1) personality measurements in the outputs of some LLMs under specific prompting configurations are reliable and valid; 2) evidence of reliability and validity of synthetic LLM personality is stronger for larger and instruction fine-tuned models; and 3) personality in LLM outputs can be shaped along desired dimensions to mimic specific human personality profiles. We discuss the application and ethical implications of the measurement and shaping method, in particular regarding responsible AI.

The field of eXplainable Artificial Intelligence (XAI) aims to bring transparency to today's powerful but opaque deep learning models. While local XAI methods explain individual predictions in form of attribution maps, thereby identifying where important features occur (but not providing information about what they represent), global explanation techniques visualize what concepts a model has generally learned to encode. Both types of methods thus only provide partial insights and leave the burden of interpreting the model's reasoning to the user. In this work we introduce the Concept Relevance Propagation (CRP) approach, which combines the local and global perspectives and thus allows answering both the "where" and "what" questions for individual predictions. We demonstrate the capability of our method in various settings, showcasing that CRP leads to more human interpretable explanations and provides deep insights into the model's representation and reasoning through concept atlases, concept composition analyses, and quantitative investigations of concept subspaces and their role in fine-grained decision making.

Systems incorporating biometric technologies have become ubiquitous in personal, commercial, and governmental identity management applications. Both cooperative (e.g. access control) and non-cooperative (e.g. surveillance and forensics) systems have benefited from biometrics. Such systems rely on the uniqueness of certain biological or behavioural characteristics of human beings, which enable for individuals to be reliably recognised using automated algorithms. Recently, however, there has been a wave of public and academic concerns regarding the existence of systemic bias in automated decision systems (including biometrics). Most prominently, face recognition algorithms have often been labelled as "racist" or "biased" by the media, non-governmental organisations, and researchers alike. The main contributions of this article are: (1) an overview of the topic of algorithmic bias in the context of biometrics, (2) a comprehensive survey of the existing literature on biometric bias estimation and mitigation, (3) a discussion of the pertinent technical and social matters, and (4) an outline of the remaining challenges and future work items, both from technological and social points of view.

Ethics as a service: a pragmatic operationalisation of AI Ethics

Jessica Morley, Anat Elhalal, Francesca Garcia +3

As the range of potential uses for Artificial Intelligence (AI), in particular machine learning (ML), has increased, so has awareness of the associated ethical issues. This increased awareness has led to the realisation that existing legislation and regulation provides insufficient protection to individuals, groups, society, and the environment from AI harms. In response to this realisation, there has been a proliferation of principle-based ethics codes, guidelines and frameworks. However, it has become increasingly clear that a significant gap exists between the theory of AI ethics principles and the practical design of AI systems. In previous work, we analysed whether it is possible to close this gap between the what and the how of AI ethics through the use of tools and methods designed to help AI developers, engineers, and designers translate principles into practice. We concluded that this method of closure is currently ineffective as almost all existing translational tools and methods are either too flexible (and thus vulnerable to ethics washing) or too strict (unresponsive to context). This raised the question: if, even with technical guidance, AI ethics is challenging to embed in the process of algorithmic design, is the entire pro-ethical design endeavour rendered futile? And, if no, then how can AI ethics be made useful for AI practitioners? This is the question we seek to address here by exploring why principles and technical translational tools are still needed even if they are limited, and how these limitations can be potentially overcome by providing theoretical grounding of a concept that has been termed Ethics as a Service.