Tootfinder

Technical Evaluation of a Disruptive Approach in Homomorphic AI
Eric Filiol
https://arxiv.org/abs/2506.11954 https://arxiv.org/pdf/25…

Technical Evaluation of a Disruptive Approach in Homomorphic AI
We present a technical evaluation of a new, disruptive cryptographic approach to data security, known as HbHAI (Hash-based Homomorphic Artificial Intelligence). HbHAI is based on a novel class of key-dependent hash functions that naturally preserve most similarity properties, most AI algorithms rely on. As a main claim, HbHAI makes now possible to analyze and process data in its cryptographically secure form while using existing native AI algorithms without modification, with unprecedented perf…

Imposing AI: Deceptive design patterns against sustainability
Ana\"elle Beignon, Thomas Thibault, Nolwenn Maudet
https://arxiv.org/abs/2508.08672 https://

Imposing AI: Deceptive design patterns against sustainability
Generative AI is being massively deployed in digital services, at a scale that will result in significant environmental harm. We document how tech companies are transforming established user interfaces to impose AI use and show how and to what extent these strategies fit within established deceptive pattern categories. We identify two main design strategies that are implemented to impose AI use in both personal and professional contexts: imposing AI features in interfaces at the expense of exis…

On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
Sarah Ball, Greg Gluch, Shafi Goldwasser, Frauke Kreuter, Omer Reingold, Guy N. Rothblum
https://arxiv.org/abs/2507.07341

On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
With the increased deployment of large language models (LLMs), one concern is their potential misuse for generating harmful content. Our work studies the alignment challenge, with a focus on filters to prevent the generation of unsafe information. Two natural points of intervention are the filtering of the input prompt before it reaches the model, and filtering the output after generation. Our main results demonstrate computational challenges in filtering both prompts and outputs. First, we sho…

Embedded Off-Switches for AI Compute
James Petrie
https://arxiv.org/abs/2509.07637 https://arxiv.org/pdf/2509.07637…

Embedded Off-Switches for AI Compute
To address the risks of increasingly capable AI systems, we introduce a hardware-level off-switch that embeds thousands of independent "security blocks" in each AI accelerator. This massively redundant architecture is designed to prevent unauthorized chip use, even against sophisticated physical attacks. Our main security block design uses public key cryptography to check the authenticity of authorization licenses, and randomly generated nonces to prevent replay attacks. We evaluate attack vect…

Technical specification of a framework for the collection of clinical images and data
Alistair Mackenzie (Royal Surrey NHS Foundation Trust, Guildford, UK), Mark Halling-Brown (Royal Surrey NHS Foundation Trust, Guildford, UK), Ruben van Engen (Dutch Expert Centre for Screening), Carlijn Roozemond (Dutch Expert Centre for Screening), Lucy Warren (Royal Surrey NHS Foundation Trust, Guildford, UK), Dominic Ward (Royal Surrey NHS Foundation Trust, Guildford, UK), Nadia Smith (Royal Surrey…

Technical specification of a framework for the collection of clinical images and data
In this report a framework for the collection of clinical images and data for use when training and validating artificial intelligence (AI) tools is described. The report contains not only information about the collection of the images and clinical data, but the ethics and information governance processes to consider ensuring the data is collected safely, and the infrastructure and agreements required to allow for the sharing of data with other groups. A key characteristic of the main collect…

AI as IA: The use and abuse of artificial intelligence (AI) for human enhancement through intellectual augmentation (IA)
Alexandre Erler, Vincent C. M\"uller
https://arxiv.org/abs/2508.16642

AI as IA: The use and abuse of artificial intelligence (AI) for human enhancement through intellectual augmentation (IA)
This paper offers an overview of the prospects and ethics of using AI to achieve human enhancement, and more broadly what we call intellectual augmentation (IA). After explaining the central notions of human enhancement, IA, and AI, we discuss the state of the art in terms of the main technologies for IA, with or without brain-computer interfaces. Given this picture, we discuss potential ethical problems, namely inadequate performance, safety, coercion and manipulation, privacy, cognitive liber…

A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical Reasoning
Michael K. Chen
https://arxiv.org/abs/2508.03366 https://arxiv.org/pd…

A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical Reasoning
General logical reasoning, defined as the ability to reason deductively on domain-agnostic tasks, continues to be a challenge for large language models (LLMs). Current LLMs fail to reason deterministically and are not interpretable. As such, there has been a recent surge in interest in neurosymbolic AI, which attempts to incorporate logic into neural networks. We first identify two main neurosymbolic approaches to improving logical reasoning: (i) the integrative approach comprising models where…

Predictive calibration for digital sun sensors using sparse submanifold convolutional neural networks
Michael Herman, Olivia J. Pinon Fischer, Dimitri N. Mavris
https://arxiv.org/abs/2508.00918

Predictive calibration for digital sun sensors using sparse submanifold convolutional neural networks
Recent developments in AI techniques for space applications mirror the success achieved in terrestrial applications. Machine learning, which excels in data rich environments, is particularly well suited to space-based computer vision applications, such as space optical attitude sensing. Of these sensors, digital sun sensors (DSS) are one of the most common and important sensors for spacecraft attitude determination. The main challenge in using the DSS for attitude estimation are sensor errors, …

ATLAS: AI-Native Receiver Test-and-Measurement by Leveraging AI-Guided Search
Mauro Belgiovine, Suyash Pradhan, Johannes Lange, Michael L\"ohning, Kaushik Chowdhury
https://arxiv.org/abs/2508.12204

ATLAS: AI-Native Receiver Test-and-Measurement by Leveraging AI-Guided Search
Industry adoption of Artificial Intelligence (AI)-native wireless receivers, or even modular, Machine Learning (ML)-aided wireless signal processing blocks, has been slow. The main concern is the lack of explainability of these trained ML models and the significant risks posed to network functionalities in case of failures, especially since (i) testing on every exhaustive case is infeasible and (ii) the data used for model training may not be available. This paper proposes ATLAS, an AI-guided a…

Factual Inconsistencies in Multilingual Wikipedia Tables
Silvia Cappa, Lingxiao Kong, Pille-Riin Peet, Fanfu Wei, Yuchen Zhou, Jan-Christoph Kalo
https://arxiv.org/abs/2507.18406

Factual Inconsistencies in Multilingual Wikipedia Tables
Wikipedia serves as a globally accessible knowledge source with content in over 300 languages. Despite covering the same topics, the different versions of Wikipedia are written and updated independently. This leads to factual inconsistencies that can impact the neutrality and reliability of the encyclopedia and AI systems, which often rely on Wikipedia as a main training source. This study investigates cross-lingual inconsistencies in Wikipedia's structured content, with a focus on tabular data…

Probability Density from Latent Diffusion Models for Out-of-Distribution Detection
Joonas J\"arve, Karl Kaspar Haavel, Meelis Kull
https://arxiv.org/abs/2508.15737 https://…

Probability Density from Latent Diffusion Models for Out-of-Distribution Detection
Despite rapid advances in AI, safety remains the main bottleneck to deploying machine-learning systems. A critical safety component is out-of-distribution detection: given an input, decide whether it comes from the same distribution as the training data. In generative models, the most natural OOD score is the data likelihood. Actually, under the assumption of uniformly distributed OOD data, the likelihood is even the optimal OOD detector, as we show in this work. However, earlier work reported …

HLLM-Creator: Hierarchical LLM-based Personalized Creative Generation
Junyi Chen, Lu Chi, Siliang Xu, Shiwei Ran, Bingyue Peng, Zehuan Yuan
https://arxiv.org/abs/2508.18118 http…

HLLM-Creator: Hierarchical LLM-based Personalized Creative Generation
AI-generated content technologies are widely used in content creation. However, current AIGC systems rely heavily on creators' inspiration, rarely generating truly user-personalized content. In real-world applications such as online advertising, a single product may have multiple selling points, with different users focusing on different features. This underscores the significant value of personalized, user-centric creative generation. Effective personalized content generation faces two main ch…

The AI Risk Spectrum: From Dangerous Capabilities to Existential Threats
Markov Grey, Charbel-Rapha\"el Segerie
https://arxiv.org/abs/2508.13700 https://

The AI Risk Spectrum: From Dangerous Capabilities to Existential Threats
As AI systems become more capable, integrated, and widespread, understanding the associated risks becomes increasingly important. This paper maps the full spectrum of AI risks, from current harms affecting individual users to existential threats that could endanger humanity's survival. We organize these risks into three main causal categories. Misuse risks, which occur when people deliberately use AI for harmful purposes - creating bioweapons, launching cyberattacks, adversarial AI attacks or d…

The Developments and Challenges towards Dexterous and Embodied Robotic Manipulation: A Survey
Gaofeng Li, Ruize Wang, Peisen Xu, Qi Ye, Jiming Chen
https://arxiv.org/abs/2507.11840

The Developments and Challenges towards Dexterous and Embodied Robotic Manipulation: A Survey
Achieving human-like dexterous robotic manipulation remains a central goal and a pivotal challenge in robotics. The development of Artificial Intelligence (AI) has allowed rapid progress in robotic manipulation. This survey summarizes the evolution of robotic manipulation from mechanical programming to embodied intelligence, alongside the transition from simple grippers to multi-fingered dexterous hands, outlining key characteristics and main challenges. Focusing on the current stage of embodie…

IoT and Older Adults: Towards Multimodal EMG and AI-Based Interaction with Smart Home
Wies{\l}aw Kope\'c, Jaros{\l}aw Kowalski, Aleksander Majda, Anna Duszyk-Bogorodzka, Anna Jaskulska, Cezary Biele
https://arxiv.org/abs/2507.19479

IoT and Older Adults: Towards Multimodal EMG and AI-Based Interaction with Smart Home
We report preliminary insights from an exploratory study on non-standard non-invasive interfaces for Smart Home Technologies (SHT). This study is part of a broader research project on effective Smart Home ecosystem Sagacity that will target older adults, impaired persons, and other groups disadvantaged in the main technology discourse. Therefore, this research is in line with a long-term research framework of the HASE research group (Human Aspects in Science and Engineering) by the Living Lab K…

A not-too-simple solution to Goodman's new riddle of induction in the age of AI
Luigi Scorzato
https://arxiv.org/abs/2507.17212 https://arxiv.org/pdf/2…

A not-too-simple solution to Goodman's new riddle of induction in the age of AI
I review the works of Gärdenfors (1990) and Scorzato (2013) and show that their combination provides an elegant solution of Goodman's new riddle of induction. The solution is based on two main ideas: (1) clarifying what is expected from a solution: understanding that philosophy of science is a science itself, with the same limitations and strengths as other scientific disciplines; (2) understanding that the concept of complexity of a model's assumptions and the concept of direct measurements m…

CAI Fluency: A Framework for Cybersecurity AI Fluency
V\'ictor Mayoral-Vilches, Jasmin Wachter, Crist\'obal R. J. Veas Chavez, Cathrin Schachner, Luis Javier Navarrete-Lozano, Mar\'ia Sanz-G\'omez
https://arxiv.org/abs/2508.13588

CAI Fluency: A Framework for Cybersecurity AI Fluency
This work introduces CAI Fluency, an an educational platform of the Cybersecurity AI (CAI) framework dedicated to democratizing the knowledge and application of cybersecurity AI tools in the global security community. The main objective of the CAI framework is to accelerate the widespread adoption and effective use of artificial intelligence-based cybersecurity solutions, pathing the way to vibe-hacking, the cybersecurity analogon to vibe-coding. CAI Fluency builds upon the Framework for AI F…

Ethics of Artificial Intelligence
Vincent C. M\"uller
https://arxiv.org/abs/2508.16658 https://arxiv.org/pdf/2508.16658…

Ethics of Artificial Intelligence
Artificial intelligence (AI) is a digital technology that will be of major importance for the development of humanity in the near future. AI has raised fundamental questions about what we should do with such systems, what the systems themselves should do, what risks they involve and how we can control these. - After the background to the field (1), this article introduces the main debates (2), first on ethical issues that arise with AI systems as objects, i.e. tools made and used by humans; her…

Grounding Rule-Based Argumentation Using Datalog
Martin Diller, Sarah Alice Gaggl, Philipp Hanisch, Giuseppina Monterosso, Fritz Rauschenbach
https://arxiv.org/abs/2508.10976 ht…

Grounding Rule-Based Argumentation Using Datalog
ASPIC+ is one of the main general frameworks for rule-based argumentation for AI. Although first-order rules are commonly used in ASPIC+ examples, most existing approaches to reason over rule-based argumentation only support propositional rules. To enable reasoning over first-order instances, a preliminary grounding step is required. As groundings can lead to an exponential increase in the size of the input theories, intelligent procedures are needed. However, there is a lack of dedicated solut…

Left Leaning Models: AI Assumptions on Economic Policy
Maxim Chupilkin
https://arxiv.org/abs/2507.15771 https://arxiv.org/pdf/2507.15…

Left Leaning Models: AI Assumptions on Economic Policy
How does AI think about economic policy? While the use of large language models (LLMs) in economics is growing exponentially, their assumptions on economic issues remain a black box. This paper uses a conjoint experiment to tease out the main factors influencing LLMs' evaluation of economic policy. It finds that LLMs are most sensitive to unemployment, inequality, financial stability, and environmental harm and less sensitive to traditional macroeconomic concerns such as economic growth, inflat…