LLM platform security: Applying a systematic evaluation framework to OpenAI's ChatGPT plugins
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 …
app ecosystem to interface with third-party services on the internet. While these apps extend …
Understanding dark patterns in home IoT devices
M Kowalczyk, JT Gunawan, D Choffnes… - Proceedings of the …, 2023 - dl.acm.org
Internet-of-Things (IoT) devices are ubiquitous, but little attention has been paid to how they
may incorporate dark patterns despite consumer protections and privacy concerns arising …
may incorporate dark patterns despite consumer protections and privacy concerns arising …
[HTML][HTML] User Perception of Smart Home Surveillance Among Adults Aged 50 Years and Older: Scoping Review
J Percy Campbell, J Buchan, CH Chu… - JMIR mHealth and …, 2024 - mhealth.jmir.org
Background Smart home technology (SHT) can be useful for aging in place or health-related
purposes. However, surveillance studies have highlighted ethical issues with SHTs …
purposes. However, surveillance studies have highlighted ethical issues with SHTs …
Spying through your voice assistants: realistic voice command fingerprinting
Voice assistants are becoming increasingly pervasive due to the convenience and
automation they provide through the voice interface. However, such convenience often …
automation they provide through the voice interface. However, such convenience often …
Behaviot: Measuring smart home iot behavior using network-inferred behavior models
Smart home IoT platforms are typically closed systems, meaning that there is poor visibility
into device behavior. Understanding device behavior is important not only for determining …
into device behavior. Understanding device behavior is important not only for determining …
Voiceblock: Privacy through real-time adversarial attacks with audio-to-audio models
P O'Reilly, A Bugler, K Bhandari… - Advances in Neural …, 2022 - proceedings.neurips.cc
As governments and corporations adopt deep learning systems to collect and analyze user-
generated audio data, concerns about security and privacy naturally emerge in areas such …
generated audio data, concerns about security and privacy naturally emerge in areas such …
Response to advertising delivered by voice assistants: The mediating role of persuasion knowledge, perceived control, social presence, and privacy concerns
NH Brinson, S Holiday, JL George - Journal of Interactive …, 2024 - Taylor & Francis
More than 40% of Americans used a voice assistant (VA) this year to aid them with a host of
tasks, including purchasing nearly $20 B in products and services. Voice-assisted …
tasks, including purchasing nearly $20 B in products and services. Voice-assisted …
Data Exposure from LLM Apps: An In-depth Investigation of OpenAI's GPTs
LLM app ecosystems are quickly maturing and supporting a wide range of use cases, which
requires them to collect excessive user data. Given that the LLM apps are developed by third …
requires them to collect excessive user data. Given that the LLM apps are developed by third …
The sa4p framework: Sensing and actuation as a privilege
Popular consumer Internet of Things (IoT) devices provide increasingly diverse sensing and
actuation capabilities. Despite their benefits, such devices prompt numerous security …
actuation capabilities. Despite their benefits, such devices prompt numerous security …
{PoliGraph}: Automated privacy policy analysis using knowledge graphs
Privacy policies disclose how an organization collects and handles personal information.
Recent work has made progress in leveraging natural language processing (NLP) to …
Recent work has made progress in leveraging natural language processing (NLP) to …