Related papers: Scheming in the wild: detecting real-world AI sche…
Generative, multimodal artificial intelligence (GenAI) offers transformative potential across industries, but its misuse poses significant risks. Prior research has shed light on the potential of advanced AI systems to be exploited for…
Open-source cyber threat intelligence (OSCTI) has become essential for keeping up with the rapidly changing threat landscape. However, current OSCTI gathering and management solutions mainly focus on structured Indicators of Compromise…
Artificial intelligence (AI) has recently seen transformative breakthroughs in the life sciences, expanding possibilities for researchers to interpret biological information at an unprecedented capacity, with novel applications and advances…
The emergence of pre-trained AI systems with powerful capabilities across a diverse and ever-increasing set of complex domains has raised a critical challenge for AI safety as tasks can become too complicated for humans to judge directly.…
Modern digital applications extensively integrate Artificial Intelligence models into their core systems, offering significant advantages for automated decision-making. However, these AI-based systems encounter reliability and safety…
Humans often rely on underlying structural patterns-schemas-to create, whether by writing stories, designing software, or composing music. Schemas help organize ideas and guide exploration, but they are often difficult to discover and…
Studies have shown that toxic behavior can cause contributors to leave, and hinder newcomers' (especially from underrepresented communities) participation in Open Source Software (OSS) projects. Thus, detection of toxic language plays a…
Analysis of an organization's computer network activity is a key component of early detection and mitigation of insider threat, a growing concern for many organizations. Raw system logs are a prototypical example of streaming data that can…
Real-world requests to AI agents are fundamentally underspecified. Natural human communication relies on shared context and unstated constraints that speakers expect listeners to infer. Current agentic benchmarks test explicit…
While Large Language Models (LLMs) are rapidly integrating into daily life, research on their risks often remains lab-based and disconnected from the problems users encounter "in the wild." While recent HCI research has begun to explore…
Analyzing Open Source Intelligence (OSINT) from large volumes of data is critical for drafting and publishing comprehensive CTI reports. This process usually follows a three-stage workflow -- triage, deep search and TI drafting. While Large…
Mistakes in AI systems are inevitable, arising from both technical limitations and sociotechnical gaps. While black-boxing AI systems can make the user experience seamless, hiding the seams risks disempowering users to mitigate fallouts…
As large language model (LLM) agents are deployed autonomously in diverse contexts, evaluating their capacity for strategic deception becomes crucial. While recent research has examined how AI systems scheme against human developers,…
Recent human-computer interaction (HCI) research has revealed a widespread misalignment between how developers design workplace artificial intelligence (AI) systems, and what workers actually need from them. Yet, little research has…
In open source software (OSS) communities, existing leadership indicators are dominantly measured by code contribution or community influence. Recent studies on emergent leadership shed light on additional dimensions such as intellectual…
While much research in artificial intelligence (AI) has focused on scaling capabilities, the accelerating pace of development makes countervailing work on producing harmless, "aligned" systems increasingly urgent. Yet research on alignment…
Due to its general-purpose nature, Generative AI is applied in an ever-growing set of domains and tasks, leading to an expanding set of risks of harm impacting people, communities, society, and the environment. These risks may arise due to…
Real-world evaluation of perception-based planning models for robotic systems, such as autonomous vehicles, can be safely and inexpensively conducted offline, i.e. by computing model prediction error over a pre-collected validation dataset…
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…
In February 2024, after building trust over two years with project maintainers by making a significant volume of legitimate contributions, GitHub user "JiaT75" self-merged a version of the XZ Utils project containing a highly sophisticated,…