國立高雄大學圖資館 |

登入

回首頁

Towards Trustworthy AI: Detecting, Understanding, and Mitigating Information Disorder /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Towards Trustworthy AI: Detecting, Understanding, and Mitigating Information Disorder /Lin Ai.
作者:	Ai, Lin,
面頁冊數:	1 electronic resource (312 pages)
附註:	Source: Dissertations Abstracts International, Volume: 87-04, Section: A.
附註:	Advisors: Hirschberg, Julia.
Contained By:	Dissertations Abstracts International87-04A.
標題:	Computer science.
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32243863
ISBN:	9798297612365

Towards Trustworthy AI: Detecting, Understanding, and Mitigating Information Disorder /
Ai, Lin,

Towards Trustworthy AI: Detecting, Understanding, and Mitigating Information Disorder /Lin Ai. - 1 electronic resource (312 pages)

Source: Dissertations Abstracts International, Volume: 87-04, Section: A.

The spread of misinformation, propaganda, and manipulative narratives -- collectively referred to as information disorder -- has emerged as a major threat to the trustworthiness of online discourse. This challenge is further intensified by the rise of large language models (LLMs), which, while offering powerful generative capabilities, also create new risks for abuse and misalignment. In this dissertation, I investigate how information disorder manifests itself and evolves across both human and AI-mediated communication channels, and explore key challenges and solutions at different stages of the landscape -- from detection and intent analysis to mitigation strategies -- through the lens of trustworthy AI.This dissertation is structured around three core stages, each addressing a distinct facet of combating information disorder. First, I develop content-based detection frameworks that integrate textual, visual, and propagation-based features to identify untrustworthy and manipulative posts on social media. Second, I examine the anatomy of information disorder by developing models that (1) capture the intent and manipulation strategies of malicious actors -- such as propaganda techniques and emotional appeals, (2) analyze audience perception, including how user traits shape susceptibility to radicalizing content, and (3) explore the emergent threat of LLMs acting as malicious agents capable of generating deceptive or coercive communication. Third, I present system-level mitigation strategies that address these threats at scale: defending against LLM-driven social engineering, improving factual control in generative outputs, curating high-quality and novel training and retrieval content through document-level distinctiveness scoring, and designing steerable, human-in-the-loop research agents that support principled alignment and intervention.Across these stages, this dissertation advances modular, interpretable, and context-aware systems that address the evolving threat landscape of information disorder. The findings lay the foundation for future research on LLM-based trust infrastructure, agent-level safety, and human-in-the-loop alignment in complex information ecosystems.

English

ISBN: 9798297612365Subjects--Topical Terms:

199325
Computer science.
Subjects--Index Terms:

Information disorder

Towards Trustworthy AI: Detecting, Understanding, and Mitigating Information Disorder /
LDR:03565nmm a22004093i 4500 001 693768
005 20260511063022.5
006 m o d
007 cr|nu||||||||
008 260819s2025 miu||||||m |||||||eng d
020 $a 9798297612365
035 $a (MiAaPQD)AAI32243863
035 $a AAI32243863
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Ai, Lin, $e author. $3 1010438
245 1 0 $a Towards Trustworthy AI: Detecting, Understanding, and Mitigating Information Disorder / $c Lin Ai.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (312 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 87-04, Section: A.
500 $a Advisors: Hirschberg, Julia.
502 $b Ph.D. $c Columbia University $d 2025.
520 $a The spread of misinformation, propaganda, and manipulative narratives -- collectively referred to as information disorder -- has emerged as a major threat to the trustworthiness of online discourse. This challenge is further intensified by the rise of large language models (LLMs), which, while offering powerful generative capabilities, also create new risks for abuse and misalignment. In this dissertation, I investigate how information disorder manifests itself and evolves across both human and AI-mediated communication channels, and explore key challenges and solutions at different stages of the landscape -- from detection and intent analysis to mitigation strategies -- through the lens of trustworthy AI.This dissertation is structured around three core stages, each addressing a distinct facet of combating information disorder. First, I develop content-based detection frameworks that integrate textual, visual, and propagation-based features to identify untrustworthy and manipulative posts on social media. Second, I examine the anatomy of information disorder by developing models that (1) capture the intent and manipulation strategies of malicious actors -- such as propaganda techniques and emotional appeals, (2) analyze audience perception, including how user traits shape susceptibility to radicalizing content, and (3) explore the emergent threat of LLMs acting as malicious agents capable of generating deceptive or coercive communication. Third, I present system-level mitigation strategies that address these threats at scale: defending against LLM-driven social engineering, improving factual control in generative outputs, curating high-quality and novel training and retrieval content through document-level distinctiveness scoring, and designing steerable, human-in-the-loop research agents that support principled alignment and intervention.Across these stages, this dissertation advances modular, interpretable, and context-aware systems that address the evolving threat landscape of information disorder. The findings lay the foundation for future research on LLM-based trust infrastructure, agent-level safety, and human-in-the-loop alignment in complex information ecosystems.
546 $a English
590 $a School code: 0054
650 4 $a Computer science. $3 199325
650 4 $a Information science. $3 190425
653 $a Information disorder
653 $a Large language models
653 $a Trustworthy AI
690 $a 0984
690 $a 0723
690 $a 0800
710 2 $a Columbia University. $b Computer Science. $3 795499
720 1 $a Hirschberg, Julia $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 87-04A.
790 $a 0054
791 $a Ph.D.
792 $a 2025
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32243863