Defending against social engineering attacks in the age of llms

L Ai, T Kumarage, A Bhattacharjee, Z Liu, Z Hui… - arxiv preprint arxiv …, 2024 - arxiv.org
The proliferation of Large Language Models (LLMs) poses challenges in detecting and
mitigating digital deception, as these models can emulate human conversational patterns …

Creation of AI-driven Smart Spaces for Enhanced Indoor Environments--A Survey

A Varol, NH Motlagh, M Leino, S Tarkoma… - arxiv preprint arxiv …, 2024 - arxiv.org
Smart spaces are ubiquitous computing environments that integrate diverse sensing and
communication technologies to enhance space functionality, optimize energy utilization, and …

Imprompter: Tricking LLM Agents into Improper Tool Use

X Fu, S Li, Z Wang, Y Liu, RK Gupta… - arxiv preprint arxiv …, 2024 - arxiv.org
Large Language Model (LLM) Agents are an emerging computing paradigm that blends
generative machine learning with tools such as code interpreters, web browsing, email, and …

WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild

Y Deng, W Zhao, J Hessel, X Ren, C Cardie… - arxiv preprint arxiv …, 2024 - arxiv.org
The increasing availability of real-world conversation data offers exciting opportunities for
researchers to study user-chatbot interactions. However, the sheer volume of this data …

Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents

IC Ngong, S Kadhe, H Wang, K Murugesan… - Workshop on Socially …, 2024 - openreview.net
Conversational agents are increasingly woven into individuals' personal lives, yet users
often underestimate the privacy risks involved. In this paper, based on the principles of …

PAPILLON: PrivAcy Preservation from Internet-based and Local Language MOdel ENsembles

L Siyan, VC Raghuram, O Khattab… - arxiv preprint arxiv …, 2024 - arxiv.org
Users can divulge sensitive information to proprietary LLM providers, raising significant
privacy concerns. While open-source models, hosted locally on the user's machine, alleviate …

Human Decision-making is Susceptible to AI-driven Manipulation

S Sabour, JM Liu, S Liu, CZ Yao, S Cui… - arxiv preprint arxiv …, 2025 - arxiv.org
Artificial Intelligence (AI) systems are increasingly intertwined with daily life, assisting users
in executing various tasks and providing guidance on decision-making. This integration …

AI Delegates with a Dual Focus: Ensuring Privacy and Strategic Self-Disclosure

X Chen, Z Zhang, F Yang, X Qin, C Du, X Cheng… - arxiv preprint arxiv …, 2024 - arxiv.org
Large language model (LLM)-based AI delegates are increasingly utilized to act on behalf of
users, assisting them with a wide range of tasks through conversational interfaces. Despite …

Rescriber: Smaller-LLM-Powered User-Led Data Minimization for Navigating Privacy Trade-offs in LLM-Based Conversational Agent

J Zhou, E Xu, Y Wu, T Li - arxiv preprint arxiv:2410.11876, 2024 - arxiv.org
The proliferation of LLM-based conversational agents has resulted in excessive disclosure
of identifiable or sensitive information. However, existing technologies fail to offer …

[PDF][PDF] Customizing Emotional Support: How Do Individuals Construct and Interact With LLM-Powered Chatbots

X Zheng, Z Li, X Gui, Y Luo - 2025 - yuhanlolo.github.io
Personalized support is essential to fulfill individuals' emotional needs and sustain their
mental well-being. Large language models (LLMs), with great customization flexibility, hold …