Research Papers

$\aleph$-IPOMDP: Mitigating Deception in a Cognitive Hierarchy with Off-Policy Counterfactual Anomaly Detection

Nitay Alon, Joseph M. Barnby, Stefan Sarkadi +3

Social agents with finitely nested opponent models are vulnerable to manipulation by agents with deeper recursive capabilities. This imbalance, rooted in logic and the theory of recursive modelling frameworks, cannot be solved directly. We propose a computational framework called $\aleph$-IPOMDP, which augments the Bayesian inference of model-based RL agents with an anomaly detection algorithm and an out-of-belief policy. Our mechanism allows agents to realize that they are being deceived, even if they cannot understand how, and to deter opponents via a credible threat. We test this framework in both a mixed-motive and a zero-sum game. Our results demonstrate the $\aleph$-mechanism's effectiveness, leading to more equitable outcomes and less exploitation by more sophisticated agents. We discuss implications for AI safety, cybersecurity, cognitive science, and psychiatry.

Deep learning models have achieved remarkable success across diverse domains. However, the intricate nature of these models often impedes a clear understanding of their decision-making processes. This is where Explainable AI (XAI) becomes indispensable, offering intuitive explanations for model decisions. In this work, we propose a simple yet highly effective approach, ScoreCAM++, which introduces modifications to enhance the promising ScoreCAM method for visual explainability. Our proposed approach involves altering the normalization function within the activation layer utilized in ScoreCAM, resulting in significantly improved results compared to previous efforts. Additionally, we apply an activation function to the upsampled activation layers to enhance interpretability. This improvement is achieved by selectively gating lower-priority values within the activation layer. Through extensive experiments and qualitative comparisons, we demonstrate that ScoreCAM++ consistently achieves notably superior performance and fairness in interpreting the decision-making process compared to both ScoreCAM and previous methods.

On the Road to Clarity: Exploring Explainable AI for World Models in a Driver Assistance System

Mohamed Roshdi, Julian Petzold, Mostafa Wahby +3

In Autonomous Driving (AD) transparency and safety are paramount, as mistakes are costly. However, neural networks used in AD systems are generally considered black boxes. As a countermeasure, we have methods of explainable AI (XAI), such as feature relevance estimation and dimensionality reduction. Coarse graining techniques can also help reduce dimensionality and find interpretable global patterns. A specific coarse graining method is Renormalization Groups from statistical physics. It has previously been applied to Restricted Boltzmann Machines (RBMs) to interpret unsupervised learning. We refine this technique by building a transparent backbone model for convolutional variational autoencoders (VAE) that allows mapping latent values to input features and has performance comparable to trained black box VAEs. Moreover, we propose a custom feature map visualization technique to analyze the internal convolutional layers in the VAE to explain internal causes of poor reconstruction that may lead to dangerous traffic scenarios in AD applications. In a second key contribution, we propose explanation and evaluation techniques for the internal dynamics and feature relevance of prediction networks. We test a long short-term memory (LSTM) network in the computer vision domain to evaluate the predictability and in future applications potentially safety of prediction models. We showcase our methods by analyzing a VAE-LSTM world model that predicts pedestrian perception in an urban traffic situation.

Artificial Intelligence algorithms have now become pervasive in multiple high-stakes domains. However, their internal logic can be obscure to humans. Explainable Artificial Intelligence aims to design tools and techniques to illustrate the predictions of the so-called black-box algorithms. The Human-Computer Interaction community has long stressed the need for a more user-centered approach to Explainable AI. This approach can benefit from research in user interface, user experience, and visual analytics. This paper proposes a visual-based method to illustrate rules paired with feature importance. A user study with 15 participants was conducted comparing our visual method with the original output of the algorithm and textual representation to test its effectiveness with users.

In computer vision, explainable AI (xAI) methods seek to mitigate the 'black-box' problem by making the decision-making process of deep learning models more interpretable and transparent. Traditional xAI methods concentrate on visualizing input features that influence model predictions, providing insights primarily suited for experts. In this work, we present an interaction-based xAI method that enhances user comprehension of image classification models through their interaction. Thus, we developed a web-based prototype allowing users to modify images via painting and erasing, thereby observing changes in classification results. Our approach enables users to discern critical features influencing the model's decision-making process, aligning their mental models with the model's logic. Experiments conducted with five images demonstrate the potential of the method to reveal feature importance through user interaction. Our work contributes a novel perspective to xAI by centering on end-user engagement and understanding, paving the way for more intuitive and accessible explainability in AI systems.

Shapley value is a widely used tool in explainable artificial intelligence (XAI), as it provides a principled way to attribute contributions of input features to model outputs. However, estimation of Shapley value requires capturing conditional dependencies among all feature combinations, which poses significant challenges in complex data environments. In this article, EmSHAP (Energy-based model for Shapley value estimation), an accurate Shapley value estimation method, is proposed to estimate the expectation of Shapley contribution function under the arbitrary subset of features given the rest. By utilizing the ability of energy-based model (EBM) to model complex distributions, EmSHAP provides an effective solution for estimating the required conditional probabilities. To further improve estimation accuracy, a GRU (Gated Recurrent Unit)-coupled partition function estimation method is introduced. The GRU network captures long-term dependencies with a lightweight parameterization and maps input features into a latent space to mitigate the influence of feature ordering. Additionally, a dynamic masking mechanism is incorporated to further enhance the robustness and accuracy by progressively increasing the masking rate. Theoretical analysis on the error bound as well as application to four case studies verified the higher accuracy and better scalability of EmSHAP in contrast to competitive methods.

The large success of deep learning based methods in Visual Question Answering (VQA) has concurrently increased the demand for explainable methods. Most methods in Explainable Artificial Intelligence (XAI) focus on generating post-hoc explanations rather than taking an intrinsic approach, the latter characterizing an interpretable model. In this work, we introduce an interpretable approach for graph-based VQA and demonstrate competitive performance on the GQA dataset. This approach bridges the gap between interpretability and performance. Our model is designed to intrinsically produce a subgraph during the question-answering process as its explanation, providing insight into the decision making. To evaluate the quality of these generated subgraphs, we compare them against established post-hoc explainability methods for graph neural networks, and perform a human evaluation. Moreover, we present quantitative metrics that correlate with the evaluations of human assessors, acting as automatic metrics for the generated explanatory subgraphs. Our implementation is available at https://github.com/DigitalPhonetics/Intrinsic-Subgraph-Generation-for-VQA.

Attention based Large Language Models (LLMs) are the state-of-the-art in natural language processing (NLP). The two most common architectures are encoders such as BERT, and decoders like the GPT models. Despite the success of encoder models, on which we focus in this work, they also bear several risks, including issues with bias or their susceptibility for adversarial attacks, signifying the necessity for explainable AI to detect such issues. While there does exist various local explainability methods focusing on the prediction of single inputs, global methods based on dimensionality reduction for classification inspection, which have emerged in other domains and that go further than just using t-SNE in the embedding space, are not widely spread in NLP. To reduce this gap, we investigate the application of DeepView, a method for visualizing a part of the decision function together with a data set in two dimensions, to the NLP domain. While in previous work, DeepView has been used to inspect deep image classification models, we demonstrate how to apply it to BERT-based NLP classifiers and investigate its usability in this domain, including settings with adversarially perturbed input samples and pre-trained, fine-tuned, and multi-task models.

Explainable Artificial Intelligence (XAI) strategies play a crucial part in increasing the understanding and trustworthiness of neural networks. Nonetheless, these techniques could potentially generate misleading explanations. Blinding attacks can drastically alter a machine learning algorithm's prediction and explanation, providing misleading information by adding visually unnoticeable artifacts into the input, while maintaining the model's accuracy. It poses a serious challenge in ensuring the reliability of XAI methods. To ensure the reliability of XAI methods poses a real challenge, we leverage statistical analysis to highlight the changes in CNN weights within a CNN following blinding attacks. We introduce a method specifically designed to limit the effectiveness of such attacks during the evaluation phase, avoiding the need for extra training. The method we suggest defences against most modern explanation-aware adversarial attacks, achieving an approximate decrease of ~99\% in the Attack Success Rate (ASR) and a ~91\% reduction in the Mean Square Error (MSE) between the original explanation and the defended (post-attack) explanation across three unique types of attacks.

Explainable artificial intelligence (XAI) plays an indispensable role in demystifying the decision-making processes of AI, especially within the healthcare industry. Clinicians rely heavily on detailed reasoning when making a diagnosis, often CT scans for specific features that distinguish between benign and malignant lesions. A comprehensive diagnostic approach includes an evaluation of imaging results, patient observations, and clinical tests. The surge in deploying deep learning models as support systems in medical diagnostics has been significant, offering advances that traditional methods could not. However, the complexity and opacity of these models present a double-edged sword. As they operate as "black boxes," with their reasoning obscured and inaccessible, there's an increased risk of misdiagnosis, which can lead to patient harm. Hence, there is a pressing need to cultivate transparency within AI systems, ensuring that the rationale behind an AI's diagnostic recommendations is clear and understandable to medical practitioners. This shift towards transparency is not just beneficial -- it's a critical step towards responsible AI integration in healthcare, ensuring that AI aids rather than hinders medical professionals in their crucial work.

Artificial intelligence (AI), although not able to currently capture the many complexities of humans, are slowly adapting to have certain capabilities of humans, many of which can revolutionize our world. AI systems, such as ChatGPT and others utilized within various industries for specific processes, have been transforming rapidly. However, this transformation can occur in an extremely concerning way if certain measures are not taken. This article touches on some of the current issues within the artificial intelligence ethical crisis, such as the concerns of discrimination within AI and false information that is becoming readily available with AI. Within this article, plausible solutions involving regulation are discussed and how they would mitigate ethical concerns. These include the self-regulation of businesses along with government regulation, and the effects these possible solutions can both have on current AI concerns.

Image captioning models are widely used to describe recent and archived pictures with the objective of improving their accessibility and retrieval. Yet, these approaches tend to be inefficient and biased at retrieving people's names. In this work we introduce AstroCaptions, a dataset for the image captioning task. This dataset specifically contains thousands of public fig-ures that are complex to identify for a traditional model. We also propose a novel post-processing method to insert identified people's names inside the caption using explainable AI tools and the grounding capabilities of vi-sion-language models. The results obtained with this method show signifi-cant improvements of captions quality and a potential of reducing halluci-nations. Up to 93.2% of the persons detected can be inserted in the image captions leading to improvements in the BLEU, ROUGE, CIDEr and METEOR scores of each captioning model.