Related papers: PRISM: A Design Framework for Open-Source Foundati…

A growing ecosystem of large, open-source foundation models has reduced the labeled data and technical expertise necessary to apply machine learning to many new problems. Yet foundation models pose a clear dual-use risk, indiscriminately…

Automating experimental protocol design and execution remains as a fundamental bottleneck in realizing self-driving laboratories. We introduce PRISM (Protocol Refinement through Intelligent Simulation Modeling), a framework that automates…

A system safety case is a compelling, comprehensible, and valid argument about the satisfaction of the safety goals of a given system operating in a given environment supported by convincing evidence. Since the publication of UL 4600 in…

Millions of users leverage generative pretrained transformer (GPT)-based language models developed by leading model providers for a wide range of tasks. To support enhanced user interaction and customization, many platforms-such as…

AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their…

Large language model (LLM) platforms, such as ChatGPT, have recently begun offering an app ecosystem to interface with third-party services on the internet. While these apps extend the capabilities of LLM platforms, they are developed by…

Large language Models (LLMs) have shown remarkable proficiency in code generation tasks across various programming languages. However, their outputs often contain subtle but critical vulnerabilities, posing significant risks when deployed…

Existing foundation models are trained on copyrighted material. Deploying these models can pose both legal and ethical risks when data creators fail to receive appropriate attribution or compensation. In the United States and several other…

Foundation models, including Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), Image Generative Models (i.e, Text-to-Image Models and Image-Editing Models), and Video Generative Models, have become essential tools with…

The Open Source Software movement has been growing exponentially for a number of years with no signs of slowing. Driving this growth is the widespread availability of libraries and frameworks that provide many functionalities. Developers…

Many developers rely on Large Language Models (LLMs) to facilitate software development. Nevertheless, these models have exhibited limited capabilities in the security domain. We introduce LLMSecGuard, a framework to offer enhanced code…

We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through scheming. Scheming is a potential threat model where AI…

In recent years, there has been a growing concern with software integrity, that is, the assurance that software has not been tampered with on the path between developers and users. This path is represented by a software development pipeline…

We propose PRISM to enable users of machine translation systems to preserve the privacy of data on their own initiative. There is a growing demand to apply machine translation systems to data that require privacy protection. While several…

Design patterns are well practices to share software development experiences. These patterns allow enhancing reusability, readability and maintainability of architecture and code of software applications. As simulation applies computerized…

As large language models evolve, Machine Unlearning has emerged to address growing concerns around user privacy, copyright infringement, and overall safety. Yet state-of-the-art (SOTA) unlearning methods often suffer from catastrophic…

The widespread adoption of web applications has made their security a critical concern and has increased the need for systematic ways to assess whether they can be considered trustworthy. However, "trust" assessment remains an open problem…

The development of cyber-physical systems can significantly benefit from domain-specific modeling and requires adequate (meta)-modeling frameworks. If such systems are designed for the safety-critical area, the systems must undergo…

Individuals lack oversight over systems that process their data. This can lead to discrimination and hidden biases that are hard to uncover. Recent data protection legislation tries to tackle these issues, but it is inadequate. It does not…

Large language models are increasingly used as planners for robotic systems, yet how safely they plan remains an open question. To evaluate safe planning systematically, we introduce DESPITE, a benchmark of 12,279 tasks spanning physical…