國立虎尾科技大學 |

Privacy Protection in Conversations.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Privacy Protection in Conversations./
作者:	Xu, Qiongkai.
面頁冊數:	1 online resource (99 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-06, Section: B.
Contained By:	Dissertations Abstracts International84-06B.
標題:	Language. -
電子資源:	click for full text (PQDT)
ISBN:	9798358422407

Privacy Protection in Conversations.
Xu, Qiongkai.

Privacy Protection in Conversations. - 1 online resource (99 pages)

Source: Dissertations Abstracts International, Volume: 84-06, Section: B.

Thesis (Ph.D.)--The Australian National University (Australia), 2022.

Includes bibliographical references

Leakage of personal information in online conversations raises serious privacy concerns. For example, malicious users might collect sensitive personal information from vulnerable users via deliberately designed conversations. This thesis tackles the problem of privacy leakage in textual conversations and proposes to mitigate the risks of privacy disclosure by detecting and rewriting the risky utterances. Previous research on privacy protection in text has a focus on manipulating the implicit semantic representations in a continuous high dimensional space, which are mostly used for eliminating trails of personal information to machine learning models. Our research has a focus on the explicit expressions of conversations, namely sequences of words or tokens, which are generally used between human interlocutors or human-computer interactions. The new setting for privacy protection in text could be applied to the conversations by individual human users, such as vulnerable people, and artificial conversational bots, such as digital personal assistants.This thesis consists of two parts, answering two research questions: How to detect the utterances with the risk of privacy leakage? and How to modify or rewrite the utterances into the ones with less private information?In the first part of this thesis, we aim to detect the utterances with privacy leakage risk and report the sensitive utterances to authorized users for approval. One of the essential challenge of the detection task is that we cannot acquire a large-scale aligned corpus for supervised training of natural language inference for private information. A compact dataset is collect to merely validate the privacy leakage detection models. We investigate weakly supervised methods to learn utterance-level inference from coarse set-level alignment signals. Then, we propose novel alignment models for utterance inference. Our approaches manage to outperform competitive baseline alignment methods. Additionally, we develop a privacy-leakage detection system integrated in Facebook Messenger to demonstrate the utility of our proposed task in real-world usage scenarios.In the second part of this thesis, we investigate two pieces of work to rewrite the privacy-leakage sentences automatically into less sensitive ones. The first work discusses obscuring personal information in form of classifiable attributes. We propose to reduce the bias of sensitive attributes, such as gender, political slant and race, using an obscured text rewriting models. The rewriting models are guided by corresponding classifiers for the personal attributes to obscure. Adversarial training and fairness risk measurement are proposed to enhance the fairness of the generators, alleviating privacy leakage of the target attributes. The second work protects personal information in the form of open-domain textual descriptions. We further explore three feasible rewriting strategies, deleting, obscuring, and steering, for privacy-aware text rewriting. We investigate the possibility of fine-tuning a pre-trained language model for privacy-aware text rewriting. Based on our dataset, we further observe the relation of rewriting strategies to their semantic spaces in a knowledge graph. Then, a simple but effective decoding method is developed to incorporate these semantic spaces into the rewriting models.As a whole, this thesis presents a comprehensive study and the first solutions in varying settings for protecting privacy in conversations. We demonstrate that both privacy leakage detection and privacy-aware text rewriting are plausible using machine learning methods. Our contributions also include novel ideas for text alignment for natural language inference, training technologies for attribute obfuscating, and open-domain knowledge guidance to text rewriting. This thesis opens up inquiries into protecting sensitive user information in conversations from the perspective of explicit text representation.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798358422407Subjects--Topical Terms:

571568
Language.
Index Terms--Genre/Form:

554714
Electronic books.

Privacy Protection in Conversations.
LDR:05249ntm a22003737 4500 001 1142534
005 20240422070857.5
006 m o d
007 cr mn ---uuuuu
008 250605s2022 xx obm 000 0 eng d
020 $a 9798358422407
035 $a (MiAaPQ)AAI30167689
035 $a (MiAaPQ)AustNatlU1885266428
035 $a AAI30167689
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Xu, Qiongkai. $3 1466895
245 1 0 $a Privacy Protection in Conversations.
264 0 $c 2022
300 $a 1 online resource (99 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: 84-06, Section: B.
500 $a Advisor: Qu, Lizhen.
502 $a Thesis (Ph.D.)--The Australian National University (Australia), 2022.
504 $a Includes bibliographical references
520 $a Leakage of personal information in online conversations raises serious privacy concerns. For example, malicious users might collect sensitive personal information from vulnerable users via deliberately designed conversations. This thesis tackles the problem of privacy leakage in textual conversations and proposes to mitigate the risks of privacy disclosure by detecting and rewriting the risky utterances. Previous research on privacy protection in text has a focus on manipulating the implicit semantic representations in a continuous high dimensional space, which are mostly used for eliminating trails of personal information to machine learning models. Our research has a focus on the explicit expressions of conversations, namely sequences of words or tokens, which are generally used between human interlocutors or human-computer interactions. The new setting for privacy protection in text could be applied to the conversations by individual human users, such as vulnerable people, and artificial conversational bots, such as digital personal assistants.This thesis consists of two parts, answering two research questions: How to detect the utterances with the risk of privacy leakage? and How to modify or rewrite the utterances into the ones with less private information?In the first part of this thesis, we aim to detect the utterances with privacy leakage risk and report the sensitive utterances to authorized users for approval. One of the essential challenge of the detection task is that we cannot acquire a large-scale aligned corpus for supervised training of natural language inference for private information. A compact dataset is collect to merely validate the privacy leakage detection models. We investigate weakly supervised methods to learn utterance-level inference from coarse set-level alignment signals. Then, we propose novel alignment models for utterance inference. Our approaches manage to outperform competitive baseline alignment methods. Additionally, we develop a privacy-leakage detection system integrated in Facebook Messenger to demonstrate the utility of our proposed task in real-world usage scenarios.In the second part of this thesis, we investigate two pieces of work to rewrite the privacy-leakage sentences automatically into less sensitive ones. The first work discusses obscuring personal information in form of classifiable attributes. We propose to reduce the bias of sensitive attributes, such as gender, political slant and race, using an obscured text rewriting models. The rewriting models are guided by corresponding classifiers for the personal attributes to obscure. Adversarial training and fairness risk measurement are proposed to enhance the fairness of the generators, alleviating privacy leakage of the target attributes. The second work protects personal information in the form of open-domain textual descriptions. We further explore three feasible rewriting strategies, deleting, obscuring, and steering, for privacy-aware text rewriting. We investigate the possibility of fine-tuning a pre-trained language model for privacy-aware text rewriting. Based on our dataset, we further observe the relation of rewriting strategies to their semantic spaces in a knowledge graph. Then, a simple but effective decoding method is developed to incorporate these semantic spaces into the rewriting models.As a whole, this thesis presents a comprehensive study and the first solutions in varying settings for protecting privacy in conversations. We demonstrate that both privacy leakage detection and privacy-aware text rewriting are plausible using machine learning methods. Our contributions also include novel ideas for text alignment for natural language inference, training technologies for attribute obfuscating, and open-domain knowledge guidance to text rewriting. This thesis opens up inquiries into protecting sensitive user information in conversations from the perspective of explicit text representation.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Language. $3 571568
650 4 $a Text categorization. $3 1464781
650 4 $a Software. $2 gtt $3 574116
650 4 $a Personal information. $3 1466893
650 4 $a Gender. $3 1214940
650 4 $a Privacy. $3 575491
650 4 $a Semantics. $3 555362
650 4 $a Computer science. $3 573171
650 4 $a Criminology. $3 563146
650 4 $a Logic. $3 558909
650 4 $a Cybercrime. $3 1109747
655 7 $a Electronic books. $2 local $3 554714
690 $a 0679
690 $a 0800
690 $a 0984
690 $a 0627
690 $a 0395
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a The Australian National University (Australia). $3 1186624
773 0 $t Dissertations Abstracts International $g 84-06B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30167689 $z click for full text (PQDT)