相关论文: An Independent Safety Evaluation of Kimi K2.5

We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that two modalities enhance each other. This includes a series of…

Open-weight general-purpose AI (GPAI) models offer significant benefits but also introduce substantial cybersecurity risks, as demonstrated by the offensive capabilities of models like DeepSeek-R1 in evaluations such as MITRE's OCCULT.…

Open-weight advanced AI models -- systems whose parameters are freely available for download and adaptation -- are reshaping the global AI landscape. As these models rapidly close the performance gap with closed alternatives, they enable…

Foundation models are powerful technologies: how they are released publicly directly shapes their societal impact. In this position paper, we focus on open foundation models, defined here as those with broadly available model weights (e.g.…

With the capability to write convincing and fluent natural language and generate code, Foundation Models present dual-use concerns broadly and within the cyber domain specifically. Generative AI has already begun to impact cyberspace…

Frontier Large Language Models (LLMs) pose unprecedented dual-use risks through the potential proliferation of chemical, biological, radiological, and nuclear (CBRN) weapons knowledge. We present the first comprehensive evaluation of 10…

Language model pretraining with next token prediction has proved effective for scaling compute but is limited to the amount of available training data. Scaling reinforcement learning (RL) unlocks a new axis for the continued improvement of…

We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection (VulnLLM-R, across C/Java/Python) and black-box web application security testing (five…

Large Language Models increasingly power critical infrastructure from healthcare to finance, yet their vulnerability to adversarial manipulation threatens system integrity and user safety. Despite growing deployment, no comprehensive…

While the widespread deployment of Large Language Models (LLMs) holds great potential for society, their vulnerabilities to adversarial manipulation and exploitation can pose serious safety, security, and ethical risks. As new threats…

This report documents the preparedness assessment of Code World Model (CWM), a model for code generation and reasoning about code from Meta. We conducted pre-release testing across domains identified in our Frontier AI Framework as…

Open-weight models provide researchers and developers with accessible foundations for diverse downstream applications. We tested the safety and security postures of eight open-weight large language models (LLMs) to identify vulnerabilities…

Open-weight large language models (LLMs) unlock huge benefits in innovation, personalization, privacy, and democratization. However, their core advantage - modifiability - opens the door to systemic risks: bad actors can trivially subvert…

The rapid progress in open-source Large Language Models (LLMs) is significantly driving AI development forward. However, there is still a limited understanding of their trustworthiness. Deploying these models at scale without sufficient…

Evaluating Large Language Models (LLMs) for safety and security remains a complex task, often requiring users to navigate a fragmented landscape of ad hoc benchmarks, datasets, metrics, and reporting formats. To address this challenge, we…

The release of open-weight large language models (LLMs) creates a tension between advancing accessible research and preventing misuse, such as malicious fine-tuning to elicit harmful content. Current safety measures struggle to preserve the…

AI leaders and safety reports increasingly warn that advances in model reasoning may enable biological misuse, including by low-expertise users, while major labs describe safeguards as expanding but still evolving rather than settled. This…

The governance of open-weight artificial intelligence (AI) models has been framed as a binary choice: openness as risk, restriction as safety. This paper challenges that framing, arguing that access restrictions, without governed…

A concern about cutting-edge or "frontier" AI foundation models is that an adversary may use the models for preparing chemical, biological, radiological, nuclear, (CBRN), cyber, or other attacks. At least two methods can identify foundation…

The rapid advancement of open-source foundation models has brought transparency and accessibility to this groundbreaking technology. However, this openness has also enabled the development of highly-capable, unsafe models, as exemplified by…