Jiho Jang


2023

pdf bib
Robust Multi-bit Natural Language Watermarking through Invariant Features
KiYoon Yoo | Wonhyuk Ahn | Jiho Jang | Nojun Kwak
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Recent years have witnessed a proliferation of valuable original natural language contents found in subscription-based media outlets, web novel platforms, and outputs of large language models. However, these contents are susceptible to illegal piracy and potential misuse without proper security measures. This calls for a secure watermarking system to guarantee copyright protection through leakage tracing or ownership identification. To effectively combat piracy and protect copyrights, a multi-bit watermarking framework should be able to embed adequate bits of information and extract the watermarks in a robust manner despite possible corruption. In this work, we explore ways to advance both payload and robustness by following a well-known proposition from image watermarking and identify features in natural language that are invariant to minor corruption. Through a systematic analysis of the possible sources of errors, we further propose a corruption-resistant infill model. Our full method improves upon the previous work on robustness by +16.8% point on average on four datasets, three corruption types, and two corruption ratios

2022

pdf bib
Detection of Adversarial Examples in Text Classification: Benchmark and Baseline via Robust Density Estimation
KiYoon Yoo | Jangho Kim | Jiho Jang | Nojun Kwak
Findings of the Association for Computational Linguistics: ACL 2022

Word-level adversarial attacks have shown success in NLP models, drastically decreasing the performance of transformer-based models in recent years. As a countermeasure, adversarial defense has been explored, but relatively few efforts have been made to detect adversarial examples. However, detecting adversarial examples may be crucial for automated tasks (e.g. review sentiment analysis) that wish to amass information about a certain population and additionally be a step towards a robust defense system. To this end, we release a dataset for four popular attack methods on four datasets and four models to encourage further research in this field. Along with it, we propose a competitive baseline based on density estimation that has the highest auc on 29 out of 30 dataset-attack-model combinations. The source code is released (https://github.com/bangawayoo/adversarial-examples-in-text-classification).