相关论文: Biothreat Benchmark Generation Framework for Evalu…

The potential for rapidly-evolving frontier artificial intelligence (AI) models, especially large language models (LLMs), to facilitate bioterrorism or access to biological weapons has generated significant policy, academic, and public…

The potential for rapidly-evolving frontier artificial intelligence (AI) models, especially large language models (LLMs), to facilitate bioterrorism or access to biological weapons has generated significant policy, academic, and public…

To accurately and confidently answer the question 'could an AI model or system increase biorisk', it is necessary to have both a sound theoretical threat model for how AI models or systems could increase biorisk and a robust method for…

As advancements in artificial intelligence (AI) propel progress in the life sciences, they may also enable the weaponisation and misuse of biological agents. This article differentiates two classes of AI tools that could pose such…

There is widespread optimism that frontier Large Language Models (LLMs) and LLM-augmented systems have the potential to rapidly accelerate scientific discovery across disciplines. Today, many benchmarks exist to measure LLM knowledge and…

Healthcare predictive analytics aids medical decision-making, diagnosis prediction and drug review analysis. Therefore, prediction accuracy is an important criteria which also necessitates robust predictive language models. However, the…

As generative AI systems, including large language models (LLMs) and diffusion models, advance rapidly, their growing adoption has led to new and complex security risks often overlooked in traditional AI risk assessment frameworks. This…

Optimization benchmarks play a fundamental role in assessing algorithm performance; however, existing artificial benchmarks often fail to capture the diversity and irregularity of real-world problem structures, while benchmarks derived from…

Threat modeling is a popular method to securely develop systems by achieving awareness of potential areas of future damage caused by adversaries. However, threat modeling for systems relying on Artificial Intelligence is still not well…

Cybersecurity threats and vulnerabilities continue to grow in number and complexity, presenting an increasing challenge for organizations worldwide. Organizations use threat modelling and bug bounty programs to address these threats, which…

The increasing use of Large Language Models (LLMs) offers significant opportunities across the engineering lifecycle, including requirements engineering, software development, process optimization, and decision support. Despite this…

Although general-purpose AI systems offer transformational opportunities in science and industry, they simultaneously raise critical concerns about safety, misuse, and potential loss of control. Despite these risks, methods for assessing…

Recent advancements in generative machine learning have enabled rapid progress in biological design tools (BDTs) such as protein structure and sequence prediction models. The unprecedented predictive accuracy and novel design capabilities…

As language models (LMs) become capable of handling a wide range of tasks, their evaluation is becoming as challenging as their development. Most generation benchmarks currently assess LMs using abstract evaluation criteria like helpfulness…

The rapid adoption of AI agents across domains has made systematic evaluation crucial for ensuring their usefulness and successful production deployment. Evaluation of AI agents typically involves using a fixed set of benchmarks and…

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 emergence of Generative AI (Gen AI) and Large Language Models (LLMs) has enabled more advanced chatbots capable of human-like interactions. However, these conversational agents introduce a broader set of operational risks that extend…

The indexing-retrieval-generation paradigm of retrieval-augmented generation (RAG) has been highly successful in solving knowledge-intensive tasks by integrating external knowledge into large language models (LLMs). However, the…

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…

AI agents powered by large language models (LLMs) are being deployed at scale, yet we lack a systematic understanding of how the choice of backbone LLM affects agent security. The non-deterministic sequential nature of AI agents complicates…