Research Papers

Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods

Zohaib Salahuddin, Henry C Woodruff, Avishek Chatterjee +1

Artificial Intelligence has emerged as a useful aid in numerous clinical applications for diagnosis and treatment decisions. Deep neural networks have shown same or better performance than clinicians in many tasks owing to the rapid increase in the available data and computational power. In order to conform to the principles of trustworthy AI, it is essential that the AI system be transparent, robust, fair and ensure accountability. Current deep neural solutions are referred to as black-boxes due to a lack of understanding of the specifics concerning the decision making process. Therefore, there is a need to ensure interpretability of deep neural networks before they can be incorporated in the routine clinical workflow. In this narrative review, we utilized systematic keyword searches and domain expertise to identify nine different types of interpretability methods that have been used for understanding deep learning models for medical image analysis applications based on the type of generated explanations and technical similarities. Furthermore, we report the progress made towards evaluating the explanations produced by various interpretability methods. Finally we discuss limitations, provide guidelines for using interpretability methods and future directions concerning the interpretability of deep neural networks for medical imaging analysis.

AI safety via debate

Geoffrey Irving, Paul Christiano, Dario Amodei

To make AI systems broadly useful for challenging real-world tasks, we need them to learn complex human goals and preferences. One approach to specifying complex goals asks humans to judge during training which agent behaviors are safe and useful, but this approach can fail if the task is too complicated for a human to directly judge. To help address this concern, we propose training agents via self play on a zero sum debate game. Given a question or proposed action, two agents take turns making short statements up to a limit, then a human judges which of the agents gave the most true, useful information. In an analogy to complexity theory, debate with optimal play can answer any question in PSPACE given polynomial time judges (direct judging answers only NP questions). In practice, whether debate works involves empirical questions about humans and the tasks we want AIs to perform, plus theoretical questions about the meaning of AI alignment. We report results on an initial MNIST experiment where agents compete to convince a sparse classifier, boosting the classifier's accuracy from 59.4% to 88.9% given 6 pixels and from 48.2% to 85.2% given 4 pixels. Finally, we discuss theoretical and practical aspects of the debate model, focusing on potential weaknesses as the model scales up, and we propose future human and computer experiments to test these properties.

A Survey of the State of Explainable AI for Natural Language Processing

Marina Danilevsky, Kun Qian, Ranit Aharonov +3

Recent years have seen important advances in the quality of state-of-the-art models, but this has come at the expense of models becoming less interpretable. This survey presents an overview of the current state of Explainable AI (XAI), considered within the domain of Natural Language Processing (NLP). We discuss the main categorization of explanations, as well as the various ways explanations can be arrived at and visualized. We detail the operations and explainability techniques currently available for generating explanations for NLP model predictions, to serve as a resource for model developers in the community. Finally, we point out the current gaps and encourage directions for future work in this important research area.

What Does Explainable AI Really Mean? A New Conceptualization of Perspectives

Derek Doran, Sarah Schulz, Tarek R. Besold

We characterize three notions of explainable AI that cut across research fields: opaque systems that offer no insight into its algo- rithmic mechanisms; interpretable systems where users can mathemat- ically analyze its algorithmic mechanisms; and comprehensible systems that emit symbols enabling user-driven explanations of how a conclusion is reached. The paper is motivated by a corpus analysis of NIPS, ACL, COGSCI, and ICCV/ECCV paper titles showing differences in how work on explainable AI is positioned in various fields. We close by introducing a fourth notion: truly explainable systems, where automated reasoning is central to output crafted explanations without requiring human post processing as final step of the generative process.

Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack

Mark Russinovich, Ahmed Salem, Ronen Eldan

Large Language Models (LLMs) have risen significantly in popularity and are increasingly being adopted across multiple applications. These LLMs are heavily aligned to resist engaging in illegal or unethical topics as a means to avoid contributing to responsible AI harms. However, a recent line of attacks, known as jailbreaks, seek to overcome this alignment. Intuitively, jailbreak attacks aim to narrow the gap between what the model can do and what it is willing to do. In this paper, we introduce a novel jailbreak attack called Crescendo. Unlike existing jailbreak methods, Crescendo is a simple multi-turn jailbreak that interacts with the model in a seemingly benign manner. It begins with a general prompt or question about the task at hand and then gradually escalates the dialogue by referencing the model's replies progressively leading to a successful jailbreak. We evaluate Crescendo on various public systems, including ChatGPT, Gemini Pro, Gemini-Ultra, LlaMA-2 70b and LlaMA-3 70b Chat, and Anthropic Chat. Our results demonstrate the strong efficacy of Crescendo, with it achieving high attack success rates across all evaluated models and tasks. Furthermore, we present Crescendomation, a tool that automates the Crescendo attack and demonstrate its efficacy against state-of-the-art models through our evaluations. Crescendomation surpasses other state-of-the-art jailbreaking techniques on the AdvBench subset dataset, achieving 29-61% higher performance on GPT-4 and 49-71% on Gemini-Pro. Finally, we also demonstrate Crescendo's ability to jailbreak multimodal models.

Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search

Sahin Cem Geyik, Stuart Ambler, Krishnaram Kenthapadi

We present a framework for quantifying and mitigating algorithmic bias in mechanisms designed for ranking individuals, typically used as part of web-scale search and recommendation systems. We first propose complementary measures to quantify bias with respect to protected attributes such as gender and age. We then present algorithms for computing fairness-aware re-ranking of results. For a given search or recommendation task, our algorithms seek to achieve a desired distribution of top ranked results with respect to one or more protected attributes. We show that such a framework can be tailored to achieve fairness criteria such as equality of opportunity and demographic parity depending on the choice of the desired distribution. We evaluate the proposed algorithms via extensive simulations over different parameter choices, and study the effect of fairness-aware ranking on both bias and utility measures. We finally present the online A/B testing results from applying our framework towards representative ranking in LinkedIn Talent Search, and discuss the lessons learned in practice. Our approach resulted in tremendous improvement in the fairness metrics (nearly three fold increase in the number of search queries with representative results) without affecting the business metrics, which paved the way for deployment to 100% of LinkedIn Recruiter users worldwide. Ours is the first large-scale deployed framework for ensuring fairness in the hiring domain, with the potential positive impact for more than 630M LinkedIn members.

An increasing number of decisions regarding the daily lives of human beings are being controlled by artificial intelligence (AI) algorithms in spheres ranging from healthcare, transportation, and education to college admissions, recruitment, provision of loans and many more realms. Since they now touch on many aspects of our lives, it is crucial to develop AI algorithms that are not only accurate but also objective and fair. Recent studies have shown that algorithmic decision-making may be inherently prone to unfairness, even when there is no intention for it. This paper presents an overview of the main concepts of identifying, measuring and improving algorithmic fairness when using AI algorithms. The paper begins by discussing the causes of algorithmic bias and unfairness and the common definitions and measures for fairness. Fairness-enhancing mechanisms are then reviewed and divided into pre-process, in-process and post-process mechanisms. A comprehensive comparison of the mechanisms is then conducted, towards a better understanding of which mechanisms should be used in different scenarios. The paper then describes the most commonly used fairness-related datasets in this field. Finally, the paper ends by reviewing several emerging research sub-fields of algorithmic fairness.

Long-Term Trends in the Public Perception of Artificial Intelligence

Ethan Fast, Eric Horvitz

Analyses of text corpora over time can reveal trends in beliefs, interest, and sentiment about a topic. We focus on views expressed about artificial intelligence (AI) in the New York Times over a 30-year period. General interest, awareness, and discussion about AI has waxed and waned since the field was founded in 1956. We present a set of measures that captures levels of engagement, measures of pessimism and optimism, the prevalence of specific hopes and concerns, and topics that are linked to discussions about AI over decades. We find that discussion of AI has increased sharply since 2009, and that these discussions have been consistently more optimistic than pessimistic. However, when we examine specific concerns, we find that worries of loss of control of AI, ethical concerns for AI, and the negative impact of AI on work have grown in recent years. We also find that hopes for AI in healthcare and education have increased over time.

The goal of the present paper is to develop and validate a questionnaire to assess AI literacy. In particular, the questionnaire should be deeply grounded in the existing literature on AI literacy, should be modular (i.e., including different facets that can be used independently of each other) to be flexibly applicable in professional life depending on the goals and use cases, and should meet psychological requirements and thus includes further psychological competencies in addition to the typical facets of AIL. We derived 60 items to represent different facets of AI Literacy according to Ng and colleagues conceptualisation of AI literacy and additional 12 items to represent psychological competencies such as problem solving, learning, and emotion regulation in regard to AI. For this purpose, data were collected online from 300 German-speaking adults. The items were tested for factorial structure in confirmatory factor analyses. The result is a measurement instrument that measures AI literacy with the facets Use & apply AI, Understand AI, Detect AI, and AI Ethics and the ability to Create AI as a separate construct, and AI Self-efficacy in learning and problem solving and AI Self-management. This study contributes to the research on AI literacy by providing a measurement instrument relying on profound competency models. In addition, higher-order psychological competencies are included that are particularly important in the context of pervasive change through AI systems.

Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature

Guangsheng Bao, Yanbin Zhao, Zhiyang Teng +2

Large language models (LLMs) have shown the ability to produce fluent and cogent content, presenting both productivity opportunities and societal risks. To build trustworthy AI systems, it is imperative to distinguish between machine-generated and human-authored content. The leading zero-shot detector, DetectGPT, showcases commendable performance but is marred by its intensive computational costs. In this paper, we introduce the concept of conditional probability curvature to elucidate discrepancies in word choices between LLMs and humans within a given context. Utilizing this curvature as a foundational metric, we present **Fast-DetectGPT**, an optimized zero-shot detector, which substitutes DetectGPT's perturbation step with a more efficient sampling step. Our evaluations on various datasets, source models, and test conditions indicate that Fast-DetectGPT not only surpasses DetectGPT by a relative around 75% in both the white-box and black-box settings but also accelerates the detection process by a factor of 340, as detailed in Table 1. See \url{https://github.com/baoguangsheng/fast-detect-gpt} for code, data, and results.

Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciences

Tim Miller, Piers Howe, Liz Sonenberg

In his seminal book `The Inmates are Running the Asylum: Why High-Tech Products Drive Us Crazy And How To Restore The Sanity' [2004, Sams Indianapolis, IN, USA], Alan Cooper argues that a major reason why software is often poorly designed (from a user perspective) is that programmers are in charge of design decisions, rather than interaction designers. As a result, programmers design software for themselves, rather than for their target audience, a phenomenon he refers to as the `inmates running the asylum'. This paper argues that explainable AI risks a similar fate. While the re-emergence of explainable AI is positive, this paper argues most of us as AI researchers are building explanatory agents for ourselves, rather than for the intended users. But explainable AI is more likely to succeed if researchers and practitioners understand, adopt, implement, and improve models from the vast and valuable bodies of research in philosophy, psychology, and cognitive science, and if evaluation of these models is focused more on people than on technology. From a light scan of literature, we demonstrate that there is considerable scope to infuse more results from the social and behavioural sciences into explainable AI, and present some key results from these fields that are relevant to explainable AI.

Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning

Artur d'Avila Garcez, Marco Gori, Luis C. Lamb +3

Current advances in Artificial Intelligence and machine learning in general, and deep learning in particular have reached unprecedented impact not only across research communities, but also over popular media channels. However, concerns about interpretability and accountability of AI have been raised by influential thinkers. In spite of the recent impact of AI, several works have identified the need for principled knowledge representation and reasoning mechanisms integrated with deep learning-based systems to provide sound and explainable models for such systems. Neural-symbolic computing aims at integrating, as foreseen by Valiant, two most fundamental cognitive abilities: the ability to learn from the environment, and the ability to reason from what has been learned. Neural-symbolic computing has been an active topic of research for many years, reconciling the advantages of robust learning in neural networks and reasoning and interpretability of symbolic representation. In this paper, we survey recent accomplishments of neural-symbolic computing as a principled methodology for integrated machine learning and reasoning. We illustrate the effectiveness of the approach by outlining the main characteristics of the methodology: principled integration of neural learning with symbolic knowledge representation and reasoning allowing for the construction of explainable AI systems. The insights provided by neural-symbolic computing shed new light on the increasingly prominent need for interpretable and accountable AI systems.