In May 2022, the Future of Privacy Forum (FPF) launched a comprehensive Report analyzing case-law under the General Data Protection Regulation (GDPR) applied to real-life cases involving Automated Decision-Making (ADM). Our research highlighted that the GDPR's protections for individuals against forms of ADM and profiling go significantly beyond Article 22 – which provides for the right of individuals not to be subject to decisions based solely on automated processing that produces legal effects or significantly impacts them, and are currently being applied by courts and Data Protection Authorities (DPAs) alike. These range from detailed transparency obligations to applying the fairness principle to avoid situations of discrimination and strict conditions for valid consent in ADM cases. As EU lawmakers are now discussing the amendments they would like to include in the European Commission (EC)'s Artificial Intelligence (AI) Act Proposal, what lessons can be drawn from GDPR enforcement precedents–as outlined in the Report–when deciding on the scope and obligations of the Act? This blog will explore: the link between the GDPR's provisions as relevant for ADM and the AI Act Proposal (1); how the AI Act's concepts of providers and users fare compared to the GDPR's controllers and processors (2); how the AI Act facilitates GDPR compliance for the deployers of AI systems (3); the opportunities to enhance or clarify obligations under the AI Act through the lens of ADM jurisprudence (4); the overlaps between GDPR enforcement precedents and the AI Act's prohibited practices or high-risk use cases (5); the issue of redress under the GDPR and the AI Act (6); and a compilation of lessons learned from the FPF Report in the context of the debates around the AI Act (7). Note: when referring to case numbers in this blog, the author is using the numbering of cases in the FPF Report.

We have terrible news if you are not all that excited about rising automation and robot power. Your anxieties about robots taking human jobs in the near future will be minimal because they may soon be granted licence to take human lives. Authorities in San Francisco have proposed a rule that would permit its military-style robots to use lethal force when necessary and in other dangerous circumstances. Typically, robots are utilised for bomb disposal and inspection. However, according to a US media report, the San Francisco Police Department intends to employ them for "criminal apprehensions, critical occurrences, exigent circumstances, executing a warrant, or during suspicious device inspections."

The European Union (hereinafter "The EU") often leads the way in establishing comprehensive legal frameworks regarding novel issues. As a reminder, it was a pioneer in the area of data protection through its adoption of the EU Data Protection Directive as early as 1995, and more recently through its enactment of the General Data Protection Regulation (GDPR) in 2016, the most severe international law in the field of data protection. Similarly, the EU is currently pushing for the adoption of a detailed regulation for artificial intelligence (hereinafter "AI") systems, the Regulation of the European Parliament and of the Council Laying Down Harmonised Rules on Artificial Intelligence (Artificial Intelligence Act) and Amending Certain Union Legislative Acts (hereinafter "the EU AI Act draft"). First presented in April 2021 by the European Commission, this law is a breakthrough endeavor which will surely have many repercussions, on the EU's level, but also internationally. Currently, in the sector of AI, the EU AI Act is a flagship initiative, which seeks to ensure the safety and trustworthiness of high-risk AI systems developed and used in the EU. It is the first law to solely address AI, and it is expected to become a "GDPR for AI".

Github Copilot, an AI tool that automatically suggests blocks of code to add as programmers type, has recently come under the scanner for the violation of open-source licenses. Earlier this month, a programmer and lawyer, Matthew Butterick, along with a team of lawyers, filed a class-action lawsuit in the US against Github Copilot, its parent company Microsoft, and AI-technology partner OpenAI, claiming that the tool profits "from the work of open-source programmers by violating the conditions of their open-source licenses." The people behind the lawsuit alleged that Copilot does not provide attribution when it reproduces code, violating the licenses governing open-source code, noted an article in Wired. Joseph Saveri, founder of the law firm behind the suit, called it the "first major step in the battle against intellectual-property violations in the tech industry arising from artificial-intelligence systems." The New York Times noted that the lawsuit may well be the first "legal attack" on the way AI is trained.

Metaverse Blockchain company Marvion, a fully owned subsidiary of Bonanza Goldfields Corp., is pleased to share that a memorandum of understanding has been signed with ComicAsia to launch "DRACULA: Rising Sun NFT" collection on Marvion's Metastudio. A total of 200 NFT listings of the collection will be live on Metastudio, allowing fans and collectors to buy and collect these via cryptocurrency and fiat payment methods. Recommended AI: How is Artificial Intelligence (AI) Changing the Future of Architecture? Commenting on the collaboration, Raymond Chua, CEO of Marvion said, "We are very excited to work with ComicAsia as we believe we can help them to tap into a wider fan base in the crypto community. The DRACULA: Rising Sun NFTs will be embedded with on-chain legal documentation to prove its provenance, and they will be compatible with multi-chains and come with royalty functionality. At Marvion, we focus on media and entertainment content, including comics. Even though content properties can be digital in nature today, they exist in the real world as intangible assets, such as intellectual property, licenses and contractual rights, with intrinsic value to be unlocked. We certainly look forward to the official launch of ComicAsia's NFTs on Metastudio."

Face recognition algorithms, when used in the real world, can be very useful, but they can also be dangerous when biased toward certain demographics. So, it is essential to understand how these algorithms are trained and what factors affect their accuracy and fairness to build better ones. In this study, we shed some light on the effect of racial distribution in the training data on the performance of face recognition models. We conduct 16 different experiments with varying racial distributions of faces in the training data. We analyze these trained models using accuracy metrics, clustering metrics, UMAP projections, face quality, and decision thresholds. We show that a uniform distribution of races in the training datasets alone does not guarantee bias-free face recognition algorithms and how factors like face image quality play a crucial role. We also study the correlation between the clustering metrics and bias to understand whether clustering is a good indicator of bias. Finally, we introduce a metric called racial gradation to study the inter and intra race correlation in facial features and how they affect the learning ability of the face recognition models. With this study, we try to bring more understanding to an essential element of face recognition training, the data. A better understanding of the impact of training data on the bias of face recognition algorithms will aid in creating better datasets and, in turn, better face recognition systems.

The UK government will amend its Online Safety Bill with measures designed to prohibit abuse of intimate images, whether or not they're real. If the bill becomes law as is, it will be illegal to share deepfake porn without the subject's consent. This would be the first ban on sharing deepfakes in the country and if the law comes into effect, violating this rule could lead to a prison sentence. Additionally, the Ministry of Justice aims to ban "downblousing," which it describes as an incident "where photos are taken down a woman's top without consent." The country banned upskirt photos, which are exactly what the term suggests, in 2019.

It is only becoming more vital as in sensitive areas like Political Profiling, Review of Essays in AI gains foothold in making critical - and in some cases, Education, etc. proliferate, there is a great need for increasing fatal - decisions in sensitive areas like Healthcare, Finance, transparency in NLP models to build trust with stakeholders Automated Driving, and such-like [8] [9] [10]. The true potential and identify biases. A lot of work in Explainable AI has aimed to devise explanation methods that give humans insights into of these recent advancements in AI can only be realised the workings and predictions of NLP models. While these if the various stakeholders manage to discern the working of methods distill predictions from complex models like Neural AI models and how their predictions are produced, as that is Networks into consumable explanations, how humans understand necessary to incorporate trust. For example, 83% of people these explanations is still widely unexplored. Innate do not understand automated decision-making systems in the human tendencies and biases can handicap the understanding of these explanations in humans, and can also lead to them criminal justice system, and subsequently, 60% oppose its use misjudging models and predictions as a result. We designed in the domain [11]. But besides securing the buy-in of endusers a randomized survey-based experiment to understand the effectiveness and developers through building trust, AI explainability of saliency-based Post-hoc explainability methods also has the potential of identifying AI inaccuracies prior in Natural Language Processing.

As the scope of machine learning broadens, we observe a recurring theme of algorithmic monoculture: the same systems, or systems that share components (e.g. training data), are deployed by multiple decision-makers. While sharing offers clear advantages (e.g. amortizing costs), does it bear risks? We introduce and formalize one such risk, outcome homogenization: the extent to which particular individuals or groups experience negative outcomes from all decision-makers. If the same individuals or groups exclusively experience undesirable outcomes, this may institutionalize systemic exclusion and reinscribe social hierarchy. To relate algorithmic monoculture and outcome homogenization, we propose the component-sharing hypothesis: if decision-makers share components like training data or specific models, then they will produce more homogeneous outcomes. We test this hypothesis on algorithmic fairness benchmarks, demonstrating that sharing training data reliably exacerbates homogenization, with individual-level effects generally exceeding group-level effects. Further, given the dominant paradigm in AI of foundation models, i.e. models that can be adapted for myriad downstream tasks, we test whether model sharing homogenizes outcomes across tasks. We observe mixed results: we find that for both vision and language settings, the specific methods for adapting a foundation model significantly influence the degree of outcome homogenization. We conclude with philosophical analyses of and societal challenges for outcome homogenization, with an eye towards implications for deployed machine learning systems.

Google is working on a secretive project that uses machine learning to train code to write, fix, and update itself. This project is part of a broader push by Google into so-called generative artificial intelligence, which uses algorithms to create images, videos, code, and more. It could have profound implications for the company's future and developers who write code. The project, which began life inside Alphabet's X research unit and was codenamed Pitchfork, moved into Google's Labs group this summer, according to people familiar with the matter. By moving into Google, it signaled its increased importance to leaders.