Related papers: CAI: An Open, Bug Bounty-Ready Cybersecurity AI

Current bias evaluation methods rarely engage with communities impacted by AI systems. Inspired by bug bounties, bias bounties have been proposed as a reward-based method that involves communities in AI bias detection by asking users of AI…

Language Model (LM) agents for cybersecurity that are capable of autonomously identifying vulnerabilities and executing exploits have potential to cause real-world impact. Policymakers, model providers, and researchers in the AI and…

The malicious use or malfunction of advanced general-purpose AI (GPAI) poses risks that, according to leading experts, could lead to the 'marginalisation or extinction of humanity.' To address these risks, there are an increasing number of…

As AI systems integrate into critical infrastructure, security gaps in AI compliance frameworks demand urgent attention. This paper audits and quantifies security risks in three major AI governance standards: NIST AI RMF 1.0, UK's AI and…

As AI systems become more advanced, concerns about large-scale risks from misuse or accidents have grown. This report analyzes the technical research into safe AI development being conducted by three leading AI companies: Anthropic, Google…

Cyber threat intelligence (CTI) is essential for effective system defense. CTI is a collection of information about current or past threats to a computer system. This information is gathered by an agent through observation, or based on a…

Artificial Intelligence (AI) has the potential to significantly benefit or harm humanity. At present, a few for-profit companies largely control the development and use of this technology, and therefore determine its outcomes. In an effort…

The EU Artificial Intelligence (AI) Act directs businesses to assess their AI systems to ensure they are developed in a way that is human-centered and trustworthy. The rapid adoption of AI in the industry has outpaced ethical evaluation…

Fairness is one of the most commonly identified ethical principles in existing AI guidelines, and the development of fair AI-enabled systems is required by new and emerging AI regulation. But most approaches to addressing the fairness of…

Current frontier AI safety evaluations emphasize static benchmarks, third-party annotations, and red-teaming. In this position paper, we argue that AI safety research should focus on human-centered evaluations that measure harmful…

As artificial intelligence systems grow more powerful, there has been increasing interest in "AI safety" research to address emerging and future risks. However, the field of AI safety remains poorly defined and inconsistently measured,…

This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by…

The rapid rise of open-weight and open-source foundation models is intensifying the obligation and reshaping the opportunity to make AI systems safe. This paper reports outcomes from the Columbia Convening on AI Openness and Safety (San…

Artificial Intelligence (AI) is poised to transform healthcare delivery through revolutionary advances in clinical decision support and diagnostic capabilities. While human expertise remains foundational to medical practice, AI-powered…

The rapid advancement and deployment of AI systems have created an urgent need for standard safety-evaluation frameworks. This paper introduces AILuminate v1.0, the first comprehensive industry-standard benchmark for assessing AI-product…

Cyber threat intelligence (CTI) is central to modern cybersecurity, providing critical insights for detecting and mitigating evolving threats. With the natural language understanding and reasoning capabilities of large language models…

Advanced AI systems offer substantial benefits but also introduce risks. In 2025, AI-enabled cyber offense has emerged as a concrete example. This technical report applies a quantitative risk modeling methodology (described in full in a…

As machine intelligence evolves, the need to test and compare the problem-solving abilities of different AI models grows. However, current benchmarks are often simplistic, allowing models to perform uniformly well and making it difficult to…

The growing integration of AI into cybersecurity is reshaping the balance between attackers and defenders. When access to advanced AI-enabled defence tools is uneven, resource-limited defenders may be unable to adopt effective protection,…

In the light of modern technological advances, Artificial Intelligence (AI) is relied upon to enhance performance, increase efficiency, and maximize gains. For Law Enforcement Agencies (LEAs), it can prove valuable in optimizing evidence…