相关论文: Peer-Preservation in Frontier Models

The governance of frontier artificial intelligence (AI) systems--particularly those capable of catastrophic misuse or systemic failure--requires institutional structures that are robust, adaptive, and innovation-preserving. This paper…

To understand the risks posed by a new AI system, we must understand what it can and cannot do. Building on prior work, we introduce a programme of new "dangerous capability" evaluations and pilot them on Gemini 1.0 models. Our evaluations…

In experiments spanning more than 100,000 trials across thirteen large language models, we show that several state-of-the-art models presented with a simple task (including Grok 4, GPT-5, and Gemini 2.5 Pro) sometimes actively subvert a…

Recent work has demonstrated the plausibility of frontier AI models scheming -- knowingly and covertly pursuing an objective misaligned with its developer's intentions. Such behavior could be very hard to detect, and if present in future…

Generative models must ensure both privacy and fairness for Trustworthy AI. While these goals have been pursued separately, recent studies propose to combine existing privacy and fairness techniques to achieve both goals. However, naively…

In federated learning (FL), balancing privacy protection, learning quality, and efficiency remains a challenge. Privacy protection mechanisms, such as Differential Privacy (DP), degrade learning quality, or, as in the case of Homomorphic…

The interactive nature of Large Language Models (LLMs), which closely track user data and context, has prompted users to share personal and private information in unprecedented ways. Even when users opt out of allowing their data to be used…

Self-recognition is a crucial metacognitive capability for AI systems, relevant not only for psychological analysis but also for safety, particularly in evaluative scenarios. Motivated by contradictory interpretations of whether models…

We evaluate the propensity of frontier models to sabotage or refuse to assist with safety research when deployed as AI research agents within a frontier AI company. We apply two complementary evaluations to four Claude models (Mythos…

Prominent AI companies are producing 'safety frameworks' as a type of voluntary self-governance. These statements purport to establish risk thresholds and safety procedures for the development and deployment of highly capable AI.…

Data forms the backbone of artificial intelligence (AI). Privacy and data protection laws thus have strong bearing on AI systems. Shielded by the rhetoric of compliance with data protection and privacy regulations, privacy-preserving…

Federated learning (FL) is a paradigm that allows several client devices and a server to collaboratively train a global model, by exchanging only model updates, without the devices sharing their local training data. These devices are often…

A series of influential studies established that large language models cannot reliably solve even simple planning tasks. We show that the latest generation of frontier models overturns this conclusion. We evaluate three families of frontier…

This article describes how technical infrastructure developed by the nonprofit OpenMined enables external scrutiny of AI systems without compromising sensitive information. Independent external scrutiny of AI systems provides crucial…

Frontier AI safety claims - published assertions that a highly capable general-purpose model is below a threshold of concern, adequately mitigated, or suitable for release - increasingly shape model deployment, governance, and public trust.…

Frontier large language models (LLMs) such as ChatGPT, Grok and Gemini are increasingly used for mental-health support with anxiety, trauma and self-worth. Most work treats them as tools or as targets of personality tests, assuming they…

To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, this report presents a comprehensive assessment of their frontier risks. Drawing on the E-T-C analysis (deployment…

If AI models can detect when they are being evaluated, the effectiveness of evaluations might be compromised. For example, models could have systematically different behavior during evaluations, leading to less reliable benchmarks for…

Many assumptions that underpin human concepts of identity do not hold for machine minds that can be copied, edited, or simulated. We argue that there exist many different coherent identity boundaries (e.g.\ instance, model, persona), and…

Data is essential to train and fine-tune today's frontier artificial intelligence (AI) models and to develop future ones. To date, academic, legal, and regulatory work has primarily addressed how data can directly harm consumers and…