Research Papers

Audits are critical mechanisms for identifying the risks and limitations of deployed artificial intelligence (AI) systems. However, the effective execution of AI audits remains incredibly difficult, and practitioners often need to make use of various tools to support their efforts. Drawing on interviews with 35 AI audit practitioners and a landscape analysis of 435 tools, we compare the current ecosystem of AI audit tooling to practitioner needs. While many tools are designed to help set standards and evaluate AI systems, they often fall short in supporting accountability. We outline challenges practitioners faced in their efforts to use AI audit tools and highlight areas for future tool development beyond evaluation -- from harms discovery to advocacy. We conclude that the available resources do not currently support the full scope of AI audit practitioners' needs and recommend that the field move beyond tools for just evaluation and towards more comprehensive infrastructure for AI accountability.

Farsight: Fostering Responsible AI Awareness During AI Application Prototyping

Zijie J. Wang, Chinmay Kulkarni, Lauren Wilcox +2

Prompt-based interfaces for Large Language Models (LLMs) have made prototyping and building AI-powered applications easier than ever before. However, identifying potential harms that may arise from AI applications remains a challenge, particularly during prompt-based prototyping. To address this, we present Farsight, a novel in situ interactive tool that helps people identify potential harms from the AI applications they are prototyping. Based on a user's prompt, Farsight highlights news articles about relevant AI incidents and allows users to explore and edit LLM-generated use cases, stakeholders, and harms. We report design insights from a co-design study with 10 AI prototypers and findings from a user study with 42 AI prototypers. After using Farsight, AI prototypers in our user study are better able to independently identify potential harms associated with a prompt and find our tool more useful and usable than existing resources. Their qualitative feedback also highlights that Farsight encourages them to focus on end-users and think beyond immediate harms. We discuss these findings and reflect on their implications for designing AI prototyping experiences that meaningfully engage with AI harms. Farsight is publicly accessible at: https://PAIR-code.github.io/farsight.

Beyond Fair Pay: Ethical Implications of NLP Crowdsourcing

Boaz Shmueli, Jan Fell, Soumya Ray +1

The use of crowdworkers in NLP research is growing rapidly, in tandem with the exponential increase in research production in machine learning and AI. Ethical discussion regarding the use of crowdworkers within the NLP research community is typically confined in scope to issues related to labor conditions such as fair pay. We draw attention to the lack of ethical considerations related to the various tasks performed by workers, including labeling, evaluation, and production. We find that the Final Rule, the common ethical framework used by researchers, did not anticipate the use of online crowdsourcing platforms for data collection, resulting in gaps between the spirit and practice of human-subjects ethics in NLP research. We enumerate common scenarios where crowdworkers performing NLP tasks are at risk of harm. We thus recommend that researchers evaluate these risks by considering the three ethical principles set up by the Belmont Report. We also clarify some common misconceptions regarding the Institutional Review Board (IRB) application. We hope this paper will serve to reopen the discussion within our community regarding the ethical use of crowdworkers.

We describe an explainable AI saliency map method for use with deep convolutional neural networks (CNN) that is much more efficient than popular fine-resolution gradient methods. It is also quantitatively similar or better in accuracy. Our technique works by measuring information at the end of each network scale which is then combined into a single saliency map. We describe how saliency measures can be made more efficient by exploiting Saliency Map Order Equivalence. We visualize individual scale/layer contributions by using a Layer Ordered Visualization of Information. This provides an interesting comparison of scale information contributions within the network not provided by other saliency map methods. Using our method instead of Guided Backprop, coarse-resolution class activation methods such as Grad-CAM and Grad-CAM++ seem to yield demonstrably superior results without sacrificing speed. This will make fine-resolution saliency methods feasible on resource limited platforms such as robots, cell phones, low-cost industrial devices, astronomy and satellite imagery.

AI agents are beginning to interact with each other directly and across internet platforms and physical environments, creating security challenges beyond traditional cybersecurity and AI safety frameworks. Free-form protocols are essential for AI's task generalization but enable new threats like secret collusion and coordinated swarm attacks. Network effects can rapidly spread privacy breaches, disinformation, jailbreaks, and data poisoning, while multi-agent dispersion and stealth optimization help adversaries evade oversight - creating novel persistent threats at a systemic level. Despite their critical importance, these security challenges remain understudied, with research fragmented across disparate fields including AI security, multi-agent learning, complex systems, cybersecurity, game theory, distributed systems, and technical AI governance. We introduce multi-agent security, a new field dedicated to securing networks of AI agents against threats that emerge or amplify through their interactions - whether direct or indirect via shared environments - with each other, humans, and institutions, and characterise fundamental security-utility and security-security trade-offs across both distributed and decentralised settings. Our preliminary work (1) taxonomizes the threat landscape arising from interacting AI agents, (2) offers applications to multi-agent security for work across diffuse subfields, and (3) proposes a unified research agenda addressing open challenges in designing secure agent systems and interaction environments. By identifying these gaps, we aim to guide research in this critical area to unlock the socioeconomic potential of large-scale agent deployment, foster public trust, and mitigate national security risks in critical infrastructure and defense contexts.

Behavioral Use Licensing for Responsible AI

Danish Contractor, Daniel McDuff, Julia Haines +5

With the growing reliance on artificial intelligence (AI) for many different applications, the sharing of code, data, and models is important to ensure the replicability and democratization of scientific knowledge. Many high-profile academic publishing venues expect code and models to be submitted and released with papers. Furthermore, developers often want to release these assets to encourage development of technology that leverages their frameworks and services. A number of organizations have expressed concerns about the inappropriate or irresponsible use of AI and have proposed ethical guidelines around the application of such systems. While such guidelines can help set norms and shape policy, they are not easily enforceable. In this paper, we advocate the use of licensing to enable legally enforceable behavioral use conditions on software and code and provide several case studies that demonstrate the feasibility of behavioral use licensing. We envision how licensing may be implemented in accordance with existing responsible AI guidelines.

Towards causal benchmarking of bias in face analysis algorithms

Guha Balakrishnan, Yuanjun Xiong, Wei Xia +1

Measuring algorithmic bias is crucial both to assess algorithmic fairness, and to guide the improvement of algorithms. Current methods to measure algorithmic bias in computer vision, which are based on observational datasets, are inadequate for this task because they conflate algorithmic bias with dataset bias. To address this problem we develop an experimental method for measuring algorithmic bias of face analysis algorithms, which manipulates directly the attributes of interest, e.g., gender and skin tone, in order to reveal causal links between attribute variation and performance change. Our proposed method is based on generating synthetic ``transects'' of matched sample images that are designed to differ along specific attributes while leaving other attributes constant. A crucial aspect of our approach is relying on the perception of human observers, both to guide manipulations, and to measure algorithmic bias. Besides allowing the measurement of algorithmic bias, synthetic transects have other advantages with respect to observational datasets: they sample attributes more evenly allowing for more straightforward bias analysis on minority and intersectional groups, they enable prediction of bias in new scenarios, they greatly reduce ethical and legal challenges, and they are economical and fast to obtain, helping make bias testing affordable and widely available. We validate our method by comparing it to a study that employs the traditional observational method for analyzing bias in gender classification algorithms. The two methods reach different conclusions. While the observational method reports gender and skin color biases, the experimental method reveals biases due to gender, hair length, age, and facial hair.

We are used to the availability of big data generated in nearly all fields of science as a consequence of technological progress. However, the analysis of such data possess vast challenges. One of these relates to the explainability of artificial intelligence (AI) or machine learning methods. Currently, many of such methods are non-transparent with respect to their working mechanism and for this reason are called black box models, most notably deep learning methods. However, it has been realized that this constitutes severe problems for a number of fields including the health sciences and criminal justice and arguments have been brought forward in favor of an explainable AI. In this paper, we do not assume the usual perspective presenting explainable AI as it should be, but rather we provide a discussion what explainable AI can be. The difference is that we do not present wishful thinking but reality grounded properties in relation to a scientific theory beyond physics.

From Clustering to Cluster Explanations via Neural Networks

Jacob Kauffmann, Malte Esders, Lukas Ruff +3

A recent trend in machine learning has been to enrich learned models with the ability to explain their own predictions. The emerging field of Explainable AI (XAI) has so far mainly focused on supervised learning, in particular, deep neural network classifiers. In many practical problems however, label information is not given and the goal is instead to discover the underlying structure of the data, for example, its clusters. While powerful methods exist for extracting the cluster structure in data, they typically do not answer the question why a certain data point has been assigned to a given cluster. We propose a new framework that can, for the first time, explain cluster assignments in terms of input features in an efficient and reliable manner. It is based on the novel insight that clustering models can be rewritten as neural networks - or 'neuralized'. Cluster predictions of the obtained networks can then be quickly and accurately attributed to the input features. Several showcases demonstrate the ability of our method to assess the quality of learned clusters and to extract novel insights from the analyzed data and representations.

Artificial intelligence (AI) systems have the potential to revolutionize clinical practices, including improving diagnostic accuracy and surgical decision-making, while also reducing costs and manpower. However, it is important to recognize that these systems may perpetuate social inequities or demonstrate biases, such as those based on race or gender. Such biases can occur before, during, or after the development of AI models, making it critical to understand and address potential biases to enable the accurate and reliable application of AI models in clinical settings. To mitigate bias concerns during model development, we surveyed recent publications on different debiasing methods in the fields of biomedical natural language processing (NLP) or computer vision (CV). Then we discussed the methods that have been applied in the biomedical domain to address bias. We performed our literature search on PubMed, ACM digital library, and IEEE Xplore of relevant articles published between January 2018 and December 2023 using multiple combinations of keywords. We then filtered the result of 10,041 articles automatically with loose constraints, and manually inspected the abstracts of the remaining 890 articles to identify the 55 articles included in this review. Additional articles in the references are also included in this review. We discuss each method and compare its strengths and weaknesses. Finally, we review other potential methods from the general domain that could be applied to biomedicine to address bias and improve fairness.The bias of AIs in biomedicine can originate from multiple sources. Existing debiasing methods that focus on algorithms can be categorized into distributional or algorithmic.

This survey article assesses and compares existing critiques of current fairness-enhancing technical interventions into machine learning (ML) that draw from a range of non-computing disciplines, including philosophy, feminist studies, critical race and ethnic studies, legal studies, anthropology, and science and technology studies. It bridges epistemic divides in order to offer an interdisciplinary understanding of the possibilities and limits of hegemonic computational approaches to ML fairness for producing just outcomes for society's most marginalized. The article is organized according to nine major themes of critique wherein these different fields intersect: 1) how "fairness" in AI fairness research gets defined; 2) how problems for AI systems to address get formulated; 3) the impacts of abstraction on how AI tools function and its propensity to lead to technological solutionism; 4) how racial classification operates within AI fairness research; 5) the use of AI fairness measures to avoid regulation and engage in ethics washing; 6) an absence of participatory design and democratic deliberation in AI fairness considerations; 7) data collection practices that entrench "bias," are non-consensual, and lack transparency; 8) the predatory inclusion of marginalized groups into AI systems; and 9) a lack of engagement with AI's long-term social and ethical outcomes. Drawing from these critiques, the article concludes by imagining future ML fairness research directions that actively disrupt entrenched power dynamics and structural injustices in society.

International AI Safety Report

Yoshua Bengio, Sören Mindermann, Daniel Privitera +93

The first International AI Safety Report comprehensively synthesizes the current evidence on the capabilities, risks, and safety of advanced AI systems. The report was mandated by the nations attending the AI Safety Summit in Bletchley, UK. Thirty nations, the UN, the OECD, and the EU each nominated a representative to the report's Expert Advisory Panel. A total of 100 AI experts contributed, representing diverse perspectives and disciplines. Led by the report's Chair, these independent experts collectively had full discretion over the report's content.