Return to search

Defending Against Misuse of Synthetic Media: Characterizing Real-world Challenges and Building Robust Defenses

Recent advances in deep generative models have enabled the generation of realistic synthetic media or deepfakes, including synthetic images, videos, and text. However, synthetic media can be misused for malicious purposes and damage users' trust in online content. This dissertation aims to address several key challenges in defending against the misuse of synthetic media.

Key contributions of this dissertation include the following: (1) Understanding challenges with the real-world applicability of existing synthetic media defenses. We curate synthetic videos and text from the wild, i.e., the Internet community, and assess the effectiveness of state-of-the-art defenses on synthetic content in the wild. In addition, we propose practical low-cost adversarial attacks, and systematically measure the adversarial robustness of existing defenses. Our findings reveal that most defenses show significant degradation in performance under real-world detection scenarios, which leads to the second thread of my work: (2) Building detection schemes with improved generalization performance and robustness for synthetic content. Most existing synthetic image detection schemes are highly content-specific, e.g., designed for only human faces, thus limiting their applicability. I propose an unsupervised content-agnostic detection scheme called NoiseScope, which does not require a priori access to synthetic images and is applicable to a wide variety of generative models, i.e., GANs. NoiseScope is also resilient against a range of countermeasures conducted by a knowledgeable attacker. For the text modality, our study reveals that state-of-the-art defenses that mine sequential patterns in the text using Transformer models are vulnerable to simple evasion schemes. We conduct further exploration towards enhancing the robustness of synthetic text detection by leveraging semantic features. / Doctor of Philosophy / Recent advances in deep generative models have enabled the generation of realistic synthetic media or deepfakes, including synthetic images, videos, and text. However, synthetic media can be misused for malicious purposes and damage users' trust in online content. This dissertation aims to address several key challenges in defending against the misuse of synthetic media.

Key contributions of this dissertation include the following: (1) Understanding challenges with the real-world applicability of existing synthetic media defenses. We curate synthetic videos and text from the Internet community, and assess the effectiveness of state-of-the-art defenses on the collected datasets. In addition, we systematically measure the robustness of existing defenses by designing practical low-cost attacks, such as changing the configuration of generative models. Our findings reveal that most defenses show significant degradation in performance under real-world detection scenarios, which leads to the second thread of my work: (2) Building detection schemes with improved generalization performance and robustness for synthetic content. Many existing synthetic image detection schemes make decisions by looking for anomalous patterns in a specific type of high-level content, e.g., human faces, thus limiting their applicability. I propose a blind content-agnostic detection scheme called NoiseScope, which does not require synthetic images for training, and is applicable to a wide variety of generative models. For the text modality, our study reveals that state-of-the-art defenses that mine sequential patterns in the text using Transformer models are not robust against simple attacks. We conduct further exploration towards enhancing the robustness of synthetic text detection by leveraging semantic features.

Identiferoai:union.ndltd.org:VTETD/oai:vtechworks.lib.vt.edu:10919/112116
Date07 October 2022
CreatorsPu, Jiameng
ContributorsComputer Science and Applications, Viswanath, Bimal, Chung, Taejoong Tijay, Yao, Danfeng, Wang, Gang, Gao, Peng
PublisherVirginia Tech
Source SetsVirginia Tech Theses and Dissertation
LanguageEnglish
Detected LanguageEnglish
TypeDissertation
FormatETD, application/pdf, application/pdf
RightsIn Copyright, http://rightsstatements.org/vocab/InC/1.0/

Page generated in 0.002 seconds