Related papers: Identifying Implicit Vulnerabilities through Perso…
Impressive progress has been made in automated problem-solving by the collaboration of large language model (LLM) based agents. However, these automated capabilities also open avenues for malicious applications. In this paper, we study a…
Leveraging persona information of users in Neural Response Generators (NRG) to perform personalized conversations has been considered as an attractive and important topic in the research of conversational agents over the past few years.…
User identification procedures, essential to the information security of systems, enable system-user interactions by exchanging data through communication links and interfaces to validate and confirm user authenticity. However, human errors…
Recent advancements in integrating large language models (LLMs) with tools have allowed the models to interact with real-world environments. However, these tool-augmented LLMs often encounter incomplete scenarios when users provide partial…
As machine learning models become increasingly complex, concerns about their robustness and trustworthiness have become more pressing. A critical vulnerability of these models is data poisoning attacks, where adversaries deliberately alter…
Being able to infer the goal of people we observe, interact with, or read stories about is one of the hallmarks of human intelligence. A prominent idea in current goal-recognition research is to infer the likelihood of an agent's goal from…
Networked multi-agent dynamical systems have been used to model how individual opinions evolve over time due to the opinions of other agents in the network. Particularly, such a model has been used to study how a planning agent can be used…
Language models (LMs) have achieved impressive accuracy across a variety of tasks but remain vulnerable to high-confidence misclassifications, also referred to as unknown unknowns (UUs). These UUs cluster into blind spots in the feature…
Security of an information system is only as strong as its weakest element. Popular elements of such system include hardware, software, network and people. Current approaches to computer security problems usually exclude people in their…
While AI techniques have found many successful applications in autonomous systems, many of them permit behaviours that are difficult to interpret and may lead to uncertain results. We follow the "verification as planning" paradigm and…
Large Language Model (LLM) agents are increasingly deployed in settings where they interact with a wide variety of people, including users who are unclear, impatient, or reluctant to share information. However, collecting real interaction…
Familiarity with a simulation platform can seduce modellers into accepting untested assumptions for convenience of implementation. These assumptions may have consequences greater than commonly suspected, and it is important that modellers…
Large language models (LLMs) make it possible to generate synthetic behavioural data at scale, offering an ethical and low-cost alternative to human experiments. Whether such data can faithfully capture psychological differences driven by…
Re-identification algorithms are used in data privacy to measure disclosure risk. They model the situation in which an adversary attacks a published database by means of linking the information of this adversary with the database. In this…
Recommender systems are used in many different applications and contexts, however their main goal can always be summarised as "connecting relevant content to interested users". Personalized recommendation algorithms achieve this goal by…
The experience and adoption of conversational search is tied to the accuracy and completeness of users' mental models -- their internal frameworks for understanding and predicting system behaviour. Thus, understanding these models can…
Person re-identification (re-ID) is a challenging problem especially when no labels are available for training. Although recent deep re-ID methods have achieved great improvement, it is still difficult to optimize deep re-ID model without…
It is becoming increasingly necessary to have monitors check for harmful behaviors during language model interactions, but text-only monitoring has not been sufficient. This is because models sometimes exhibit strategic deception and…
Operationalizing human values alongside functional and adaptation requirements remains challenging due to their ambiguous, pluralistic, and context-dependent nature. Explicit representations are needed to support the elicitation, analysis,…
Shared mental models are critical to team success; however, in practice, team members may have misaligned models due to a variety of factors. In safety-critical domains (e.g., aviation, healthcare), lack of shared mental models can lead to…