Federated Learning (FL) enables collaborative deep learning training across multiple participants without exposing sensitive personal data. However, the distributed nature of FL and the unvetted participants' data makes it vulnerable to backdoor attacks. In these attacks, adversaries inject malicious functionality into the centralized model during training, leading to intentional misclassifications for specific adversary-chosen inputs. While previous research has demonstrated successful injections of persistent backdoors in FL, the persistence also poses a challenge, as their existence in the centralized model can prompt the central aggregation server to take preventive measures to penalize the adversaries. Therefore, this paper proposes a methodology that enables adversaries to effectively remove backdoors from the centralized model upon achieving their objectives or upon suspicion of possible detection. The proposed approach extends the concept of machine unlearning and presents strategies to preserve the performance of the centralized model and simultaneously prevent over-unlearning of information unrelated to backdoor patterns, making the adversaries stealthy while removing backdoors. To the best of our knowledge, this is the first work that explores machine unlearning in FL to remove backdoors to the benefit of adversaries. Exhaustive evaluation considering image classification scenarios demonstrates the efficacy of the proposed method in efficient backdoor removal from the centralized model, injected by state-of-the-art attacks across multiple configurations.

Machine learning algorithms that aid human decision-making may inadvertently discriminate against certain protected groups. We formalize direct discrimination as a direct causal effect of the protected attributes on the decisions, while induced discrimination as a change in the causal influence of non-protected features associated with the protected attributes. The measurements of marginal direct effect (MDE) and SHapley Additive exPlanations (SHAP) reveal that state-of-the-art fair learning methods can induce discrimination via association or reverse discrimination in synthetic and real-world datasets. To inhibit discrimination in algorithmic systems, we propose to nullify the influence of the protected attribute on the output of the system, while preserving the influence of remaining features. We introduce and study post-processing methods achieving such objectives, finding that they yield relatively high model accuracy, prevent direct discrimination, and diminishes various disparity measures, e.g., demographic disparity.

Abstract-- This paper presents a study of the interconnectivity and interdependence of various Artificial intelligence (AI) technologies through the use of centrality measures, clustering coefficients, and degree of fusion measures. By analyzing the technologies through different time windows and quantifying their importance, we have revealed important insights into the crucial components shaping the AI landscape and the maturity level of the domain. The results of this study have significant implications for future development and advancements in artificial intelligence and provide a clear understanding of key technology areas of fusion. Furthermore, this paper contributes to AI public policy research by offering a data-driven perspective on the current state and future direction of the field. However, it is important to acknowledge the limitations of this research and call for further studies to build on these results. With these findings, we hope to inform and guide future research in the field of AI, contributing to its continued growth and success. AI has the potential to revolutionize a wide range of industries from healthcare and finance to transportation and agriculture [1] last but not least environmental hard and societal changes [2]. With the ability to analyze vast amounts of data and automate tasks that were once exclusively performed by humans, AI is reshaping the way we live and work. Given the potential of AI, it is essential to study and understand its applications, fusion of technologies, changes over the years in the domain as well as societal impacts. This understanding is crucial for policymakers, as they must develop effective policies that keep pace with the rapid advancement of AI technology. Moreover, the study of AI is also relevant for individuals, businesses, and organizations, as they must be prepared to adapt to the changes brought about by AI. The study of AI is crucial in today's era to unlock the full potential of this groundbreaking technology and to address the challenges and opportunities it presents.

If autonomous AI systems are to be reliably safe in novel situations, they will need to incorporate general principles guiding them to recognize and avoid harmful behaviours. Such principles may need to be supported by a binding system of regulation, which would need the underlying principles to be widely accepted. They should also be specific enough for technical implementation. Drawing inspiration from law, this article explains how negative human rights could fulfil the role of such principles and serve as a foundation both for an international regulatory system and for building technical safety constraints for future AI systems.

Public attention towards explainability of artificial intelligence (AI) systems has been rising in recent years to offer methodologies for human oversight. This has translated into the proliferation of research outputs, such as from Explainable AI, to enhance transparency and control for system debugging and monitoring, and intelligibility of system process and output for user services. Yet, such outputs are difficult to adopt on a practical level due to a lack of a common regulatory baseline, and the contextual nature of explanations. Governmental policies are now attempting to tackle such exigence, however it remains unclear to what extent published communications, regulations, and standards adopt an informed perspective to support research, industry, and civil interests. In this study, we perform the first thematic and gap analysis of this plethora of policies and standards on explainability in the EU, US, and UK. Through a rigorous survey of policy documents, we first contribute an overview of governmental regulatory trajectories within AI explainability and its sociotechnical impacts. We find that policies are often informed by coarse notions and requirements for explanations. This might be due to the willingness to conciliate explanations foremost as a risk management tool for AI oversight, but also due to the lack of a consensus on what constitutes a valid algorithmic explanation, and how feasible the implementation and deployment of such explanations are across stakeholders of an organization. Informed by AI explainability research, we conduct a gap analysis of existing policies, leading us to formulate a set of recommendations on how to address explainability in regulations for AI systems, especially discussing the definition, feasibility, and usability of explanations, as well as allocating accountability to explanation providers.

Supervised learning systems are trained using historical data and, if the data was tainted by discrimination, they may unintentionally learn to discriminate against protected groups. We propose that fair learning methods, despite training on potentially discriminatory datasets, shall perform well on fair test datasets. Such dataset shifts crystallize application scenarios for specific fair learning methods. For instance, the removal of direct discrimination can be represented as a particular dataset shift problem. For this scenario, we propose a learning method that provably minimizes model error on fair datasets, while blindly training on datasets poisoned with direct additive discrimination. The method is compatible with existing legal systems and provides a solution to the widely discussed issue of protected groups' intersectionality by striking a balance between the protected groups. Technically, the method applies probabilistic interventions, has causal and counterfactual formulations, and is computationally lightweight - it can be used with any supervised learning model to prevent discrimination via proxies while maximizing model accuracy for business necessity.

Harmful content is pervasive on social media, poisoning online communities and negatively impacting participation. A common approach to address this issue is to develop detection models that rely on human annotations. However, the tasks required to build such models expose annotators to harmful and offensive content and may require significant time and cost to complete. Generative AI models have the potential to understand and detect harmful content. To investigate this potential, we used ChatGPT and compared its performance with MTurker annotations for three frequently discussed concepts related to harmful content: Hateful, Offensive, and Toxic (HOT). We designed five prompts to interact with ChatGPT and conducted four experiments eliciting HOT classifications. Our results show that ChatGPT can achieve an accuracy of approximately 80% when compared to MTurker annotations. Specifically, the model displays a more consistent classification for non-HOT comments than HOT comments compared to human annotations. Our findings also suggest that ChatGPT classifications align with provided HOT definitions, but ChatGPT classifies "hateful" and "offensive" as subsets of "toxic." Moreover, the choice of prompts used to interact with ChatGPT impacts its performance. Based on these in-sights, our study provides several meaningful implications for employing ChatGPT to detect HOT content, particularly regarding the reliability and consistency of its performance, its understand-ing and reasoning of the HOT concept, and the impact of prompts on its performance. Overall, our study provides guidance about the potential of using generative AI models to moderate large volumes of user-generated content on social media.

Check out what's clicking on Foxnews.com. Leaders of the U.S. Federal Trade Commission said on Tuesday the agency would pursue companies who misuse artificial intelligence to violate laws against discrimination or be deceptive. The sudden popularity of Microsoft-backed OpenAI's ChatGPT this year has prompted calls for regulation amid concerns around the world about the possible use of the innovation for wrongdoing even as companies are seeking ways to use it to enhance efficiency. In a congressional hearing, FTC Chair Lina Khan and Commissioners Rebecca Slaughter and Alvaro Bedoya were asked about concerns that recent innovation in artificial intelligence, which can be used to produce high quality deep fakes, could be used to make more effective scams or otherwise violate laws. FTC Chair Lina Khan testifies on Capitol Hill in Washington on April 21, 2021.

IT IS increasingly obvious that we are on the cusp of a revolution in artificial intelligence that will be no less profound than the arrival of the printing press or the internet, as we explore in this special issue. Nobody can say for sure exactly what this future will be, but optimists – including many of those working in the companies behind the technologies – foresee one in which AI will allow us to live our best lives (see "How this moment for AI will change society forever").

Sundar Pichai told '60 Minutes' that the state of the technology is still somewhat of a black box to researchers. Several Republican senators are suggesting they are open to discussing how Congress can step in to regulate artificial intelligence systems after Senate Majority Leader Chuck Schumer, D-N.Y., announced he wants to put guardrails on the rapidly advancing sector. Multiple senators told Fox News Digital on Tuesday that they were concerned with the pace of unchecked AI advancement, though some also warned about the implications of hindering the industry's growth at a time when adversaries like China are moving full steam ahead to integrate AI into their own military and intelligence-gathering capabilities. None had seen Schumer's proposal, which is still in its very early stages. Sen. Josh Hawley, R-Mo., cautioned that he was "no expert" in the complex field but said he was "concerned" about the possible effects of AI on society.