Yoonjin Kim

Jiameng Pu, Zain Sarwar, Sifat Muhammad Abdullah et al.

Recent advances in generative models for language have enabled the creation of convincing synthetic text or deepfake text. Prior work has demonstrated the potential for misuse of deepfake text to mislead content consumers. Therefore, deepfake text detection, the task of discriminating between human and machine-generated text, is becoming increasingly critical. Several defenses have been proposed for deepfake text detection. However, we lack a thorough understanding of their real-world applicability. In this paper, we collect deepfake text from 4 online services powered by Transformer-based tools to evaluate the generalization ability of the defenses on content in the wild. We develop several low-cost adversarial attacks, and investigate the robustness of existing defenses against an adaptive attacker. We find that many defenses show significant degradation in performance under our evaluation scenarios compared to their original claimed performance. Our evaluation shows that tapping into the semantic information in the text content is a promising approach for improving the robustness and generalization performance of deepfake text detection schemes.

Aditya Bharadwaj, David Gwizdala, Yoonjin Kim et al.

Modern experiments in many disciplines generate large quantities of network (graph) data. Researchers require aesthetic layouts of these networks that clearly convey the domain knowledge and meaning. However, the problem remains challenging due to multiple conflicting aesthetic criteria and complex domain-specific constraints. In this paper, we present a strategy for generating visualizations that can help network biologists understand the protein interactions that underlie processes that take place in the cell. Specifically, we have developed Flud, an online game with a purpose (GWAP) that allows humans with no expertise to design biologically meaningful graph layouts with the help of algorithmically generated suggestions. Further, we propose a novel hybrid approach for graph layout wherein crowdworkers and a simulated annealing algorithm build on each other's progress. To showcase the effectiveness of Flud, we recruited crowd workers on Amazon Mechanical Turk to lay out complex networks that represent signaling pathways. Our results show that the proposed hybrid approach outperforms state-of-the-art techniques for graphs with a large number of feedback loops. We also found that the algorithmically generated suggestions guided the players when they are stuck and helped them improve their score. Finally, we discuss broader implications for mixed-initiative interactions in human computation games.