Artificial intelligence is poised to deliver tremendous benefits to society. But, as many have pointed out, it could also bring unprecedented new horrors. As a general-purpose technology, the same tools that will advance scientific discovery could also be used to develop cyber, chemical, or biological weapons. Governing AI will require widely sharing its benefits while keeping the most powerful AI out of the hands of bad actors. The good news is that there is already a template on how to do just that.

After Apple's product launch event this week, WIRED did a deep dive on the company's new secure server environment, known as Private Cloud Compute, which attempts to replicate in the cloud the security and privacy of processing data locally on users' individual devices. The goal is to minimize possible exposure of data processed for Apple Intelligence, the company's new AI platform. In addition to hearing about PCC from Apple's senior vice president of software engineering, Craig Federighi, WIRED readers also received a first look at content generated by Apple Intelligence's "Image Playground" feature as part of crucial updates on the recent birthday of Federighi's dog Bailey. Turning to privacy protection of a very different kind in another new AI service, WIRED looked at how users of the social media platform X can keep their data from being slurped up by the "unhinged" generative AI tool from xAI known as Grok AI. And in other news about Apple products, researchers developed a technique for using eye tracking to discern passwords and PINs people typed using 3D Apple Vision Pro avatars--a sort of keylogger for mixed reality.

This paper examines the governance of multimodal large language models (MM-LLMs) through individual and collective deliberation, focusing on analyses of politically sensitive videos. We conducted a two-step study: first, interviews with 10 journalists established a baseline understanding of expert video interpretation; second, 114 individuals from the general public engaged in deliberation using Inclusive.AI, a platform that facilitates democratic decision-making through decentralized autonomous organization (DAO) mechanisms. Our findings show that while experts emphasized emotion and narrative, the general public prioritized factual clarity, objectivity of the situation, and emotional neutrality. Additionally, we explored the impact of different governance mechanisms: quadratic vs. weighted ranking voting and equal vs. 20-80 power distributions on users decision-making on how AI should behave. Specifically, quadratic voting enhanced perceptions of liberal democracy and political equality, and participants who were more optimistic about AI perceived the voting process to have a higher level of participatory democracy. Our results suggest the potential of applying DAO mechanisms to help democratize AI governance.

As AI systems become more advanced, ensuring their alignment with a diverse range of individuals and societal values becomes increasingly critical. But how can we capture fundamental human values and assess the degree to which AI systems align with them? We introduce ValueCompass, a framework of fundamental values, grounded in psychological theory and a systematic review, to identify and evaluate human-AI alignment. We apply ValueCompass to measure the value alignment of humans and language models (LMs) across four real-world vignettes: collaborative writing, education, public sectors, and healthcare. Our findings uncover risky misalignment between humans and LMs, such as LMs agreeing with values like "Choose Own Goals", which are largely disagreed by humans. We also observe values vary across vignettes, underscoring the necessity for context-aware AI alignment strategies. This work provides insights into the design space of human-AI alignment, offering foundations for developing AI that responsibly reflects societal values and ethics.

While generative models have made significant advancements in recent years, they also raise concerns such as privacy breaches and biases. Machine unlearning has emerged as a viable solution, aiming to remove specific training data, e.g., containing private information and bias, from models. In this paper, we study the machine unlearning problem in Image-to-Image (I2I) generative models. Previous studies mainly treat it as a single objective optimization problem, offering a solitary solution, thereby neglecting the varied user expectations towards the trade-off between complete unlearning and model utility. To address this issue, we propose a controllable unlearning framework that uses a control coefficient $\varepsilon$ to control the trade-off. We reformulate the I2I generative model unlearning problem into a $\varepsilon$-constrained optimization problem and solve it with a gradient-based method to find optimal solutions for unlearning boundaries. These boundaries define the valid range for the control coefficient. Within this range, every yielded solution is theoretically guaranteed with Pareto optimality. We also analyze the convergence rate of our framework under various control functions. Extensive experiments on two benchmark datasets across three mainstream I2I models demonstrate the effectiveness of our controllable unlearning framework.

In tandem with the recent advancements in foundation model research, there has been a surge of generative music AI applications within the past few years. As the idea of AI-generated or AI-augmented music becomes more mainstream, many researchers in the music AI community may be wondering what avenues of research are left. With regards to music generative models, we outline the current areas of research with significant room for exploration. Firstly, we pose the question of foundational representation of these generative models and investigate approaches towards explainability. Next, we discuss the current state of music datasets and their limitations. We then overview different generative models, forms of evaluating these models, and their computational constraints/limitations. Subsequently, we highlight applications of these generative models towards extensions to multiple modalities and integration with artists' workflow as well as music education systems. Finally, we survey the potential copyright implications of generative music and discuss strategies for protecting the rights of musicians. While it is not meant to be exhaustive, our survey calls to attention a variety of research directions enabled by music foundation models.

To address unfairness issues in federated learning (FL), contemporary approaches typically use frequent model parameter updates and transmissions between the clients and server. In such a process, client-specific information (e.g., local dataset size or data-related fairness metrics) must be sent to the server to compute, e.g., aggregation weights. All of this results in high transmission costs and the potential leakage of client information. As an alternative, we propose a strategy that promotes fair predictions across clients without the need to pass information between the clients and server iteratively and prevents client data leakage. For each client, we first use their local dataset to obtain a synthetic dataset by solving a bilevel optimization problem that addresses unfairness concerns during the learning process. We then pass each client's synthetic dataset to the server, the collection of which is used to train the server model using conventional machine learning techniques (that do not take fairness metrics into account). Thus, we eliminate the need to handle fairness-specific aggregation weights while preserving client privacy. Our approach requires only a single communication between the clients and the server, thus making it computationally cost-effective, able to maintain privacy, and able to ensuring fairness. We present empirical evidence to demonstrate the advantages of our approach. The results illustrate that our method effectively uses synthetic data as a means to mitigate unfairness and preserve client privacy.

For the second time in just a few years, South Korean women took to the streets of Seoul to demand an end to sexual abuse. When the country spearheaded Asia's #MeToo movement, the culprit was molka – spy cams used to record women without their knowledge. Now their fury was directed at an epidemic of deepfake pornography. For Juhee Jin, 26, a Seoul resident who advocates for women's rights, the emergence of this new menace, in which women and girls are again the targets, was depressingly predictable. "This should have been addressed a long time ago," says Jin, a translator.

When a company triples in value in just a few months, as computer chip company Nvidia has, investors take notice. But regulators do too, because they know from experience how monopolies engage in illegal anti-competitive behavior that squashes competitors and manipulates the market to expand their dominance. The US Department of Justice (as well as other competition authorities and tech observers) suspects Nvidia has used such tactics to entrench its chips monopoly, and last month it was reported that the Department of Justice was opening an antitrust investigation. Before the pandemic, few beyond video game enthusiasts – whose top-of-the-line gaming computers and consoles are built on high-capacity Nvidia chips – had ever heard of the company. But thanks to the generative AI boom, Nvidia has become one of the fastest-growing companies ever, and its chips have powered every important AI milestone – including OpenAI's development of ChatGPT, which holds two-thirds of the AI business tools market.

Generative Artificial Intelligence (AI) models may carry societal transformation to an extent demanding a delicate balance between opportunity and risk. This manuscript is the first of a series of White Papers informing the development of IEEE-SA's p3995: `Standard for the Implementation of Safeguards, Controls, and Preventive Techniques for Artificial Intelligence (AI) Models', Chair: Marina Cort\^{e}s (https://standards.ieee.org/ieee/3395/11378/). In this first horizon-scanning we identify key attention areas for standards activities in AI. We examine different principles for regulatory efforts, and review notions of accountability, privacy, data rights and mis-use. As a safeguards standard we devote significant attention to the stability of global infrastructures and consider a possible overdependence on cloud computing that may result from densely coupled AI components. We review the recent cascade-failure-like Crowdstrike event in July 2024, as an illustration of potential impacts on critical infrastructures from AI-induced incidents in the (near) future. It is the first of a set of articles intended as White Papers informing the audience on the standard development. Upcoming articles will focus on regulatory initiatives, technology evolution and the role of AI in specific domains.