Logo des Repositoriums
 

ChatAnalysis: Can GPT-4 undermine Privacy in Smart Homes with Data Analysis?

Kurzanzeige
dc.contributor.authorJüttner, Victor
dc.contributor.authorFleig, Arthur
dc.contributor.authorBuchmann, Erik
dc.date.accessioned2024-08-21T11:08:34Z
dc.date.available2024-08-21T11:08:34Z
dc.date.issued2024
dc.description.abstractInteracting with Large Language Models (LLMs) has become as easy as sending a text message to a friend, contributing to their widespread use in various fields. We can ask them questions, instruct them to imitate characters, or have them generate images with just a few sentences. Document loaders for LLMs allow us to send tables or raw sensor data, which can then be analyzed to answer any questions we may have. Historically, such data analysis required specialized knowledge of statistics, programming, and data handling, which has been a barrier for many. This study examines the extent to which this barrier is falling due to the capabilities of LLMs, and to which extent it facilitates the misuse of data to undermine privacy. We examine the ability of GPT-4 to interpret human activity through smart home sensor data. Specifically, we evaluate how effectively GPT-4 can infer daily activities, generalize behavior, and detect anomalies in human behavior. Our methodology utilizes sensor data collected over time from wide-spread connected devices such as lamps, motion sensors, doors, and thermometers, which are adapted from the CASAS project dataset. Our key findings show that while GPT-4 can infer certain daily activities and detect anomalies, its ability to generalize behavior patterns over a week is notably limited.en
dc.identifier.doi10.18420/muc2024-mci-ws13-143
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/44282
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofMensch und Computer 2024 - Workshopband
dc.relation.ispartofseriesMensch und Computer
dc.rightshttp://purl.org/eprint/accessRights/RestrictedAccess
dc.rights.urihttp://purl.org/eprint/accessRights/RestrictedAccess
dc.titleChatAnalysis: Can GPT-4 undermine Privacy in Smart Homes with Data Analysis?en
dc.typeText/Workshop Paper
gi.conference.date1.-4. September 2024
gi.conference.locationKarlsruhe
gi.conference.sessiontitleMCI-WS13: Workshop Mensch-Maschine-Interaktion in sicherheitskritischen Systemen

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild
Name:
muc2024-mci-ws13-143.pdf
Größe:
481.03 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

Workshopband MuC 2024