Related papers: Identifying Implicit Vulnerabilities through Perso…
Explaining black-box Artificial Intelligence (AI) models is a cornerstone for trustworthy AI and a prerequisite for its use in safety critical applications such that AI models can reliably assist humans in critical decisions. However,…
Privacy policy documents are often lengthy, complex, and difficult for non-expert users to interpret, leading to a lack of transparency regarding the collection, processing, and sharing of personal data. As concerns over online privacy…
Modern machine learning systems use models trained on ever-growing corpora. Typically, metadata such as ownership, access control, or licensing information is ignored during training. Instead, to mitigate privacy risks, we rely on generic…
Mental models play an important role in whether user interaction with intelligent systems, such as dialog systems is successful or not. Adaptive dialog systems present the opportunity to align a dialog agent's behavior with heterogeneous…
Personas are commonly used in software projects to gain a better understanding of end-users' needs. However, there is a limited understanding of their usage and effectiveness in practice. This paper presents the results of a two-step…
Persona-driven large language models (LLMs) require consistent behavioral tendencies across interactions to simulate human-like personality traits, such as persistence or reliability. However, current LLMs often lack stable internal…
As large language models (LLMs) become ubiquitous in our daily tasks and digital interactions, associated privacy risks are increasingly in focus. While LLM privacy research has primarily focused on the leakage of model training data, it…
The field of AI alignment is concerned with AI systems that pursue unintended goals. One commonly studied mechanism by which an unintended goal might arise is specification gaming, in which the designer-provided specification is flawed in a…
Interacting with human agents in complex scenarios presents a significant challenge for robotic navigation, particularly in environments that necessitate both collision avoidance and collaborative interaction, such as indoor spaces. Unlike…
In cybersecurity, vulnerability assessment has typically focused on identifying and measuring vulnerabilities within digital assets and technical infrastructures. However, there is growing recognition that this approach alone is inadequate…
Current evaluations of tool-integrated LLM agents typically focus on end-to-end tool-usage evaluation while neglecting their stability. This limits their real-world applicability, as various internal or external factors can cause agents to…
Although machine learning is widely used in practice, little is known about practitioners' understanding of potential security challenges. In this work, we close this substantial gap and contribute a qualitative study focusing on…
Many assumptions that underpin human concepts of identity do not hold for machine minds that can be copied, edited, or simulated. We argue that there exist many different coherent identity boundaries (e.g.\ instance, model, persona), and…
As conversational AI systems become more realistic and widely deployed, users are increasingly uncertain about whether they are interacting with a human or an AI system. When AI identity is unclear, users may unwittingly share sensitive…
Can machine learning models for recommendation be easily fooled? While the question has been answered for hand-engineered fake user profiles, it has not been explored for machine learned adversarial attacks. This paper attempts to close…
Bots are automated social media users that can be used to amplify (mis)information and sow harmful discourse. In order to effectively influence users, bots can be generated to reproduce human user behavior. Indeed, people tend to trust…
Susceptibility to misinformation describes the degree of belief in unverifiable claims, a latent aspect of individuals' mental processes that is not observable. Existing susceptibility studies heavily rely on self-reported beliefs, which…
Finetuning can significantly modify the behavior of large language models, including introducing harmful or unsafe behaviors. To study these risks, researchers develop model organisms: models finetuned to exhibit specific known behaviors…
We investigate the real-time estimation of human situation awareness using observations from a robot teammate with limited visibility. In human factors and human-autonomy teaming, it is recognized that individuals navigate their…
Information visualization plays a key role in business intelligence analytics. With ever larger amounts of data that need to be interpreted, using the right visualizations is crucial in order to understand the underlying patterns and…