Shixin Guo

Shixin Guo

Auto-generated profile, based on publicly available information

Shixin Guo

College of Computer Science and Technology, Zhejiang Normal University, Jinhua, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 December 2023 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
Hao PengHao Peng
Hao Peng
SGShixin Guo
Shixin Guo
DZDandan Zhao
Dandan Zhao
XZXuhong Zhang
Xuhong Zhang
JHJianMin Han
JianMin Han
MZMing Zhong
Ming Zhong
Designing a query-efficient attack strategy to generate high-quality adversarial examples under the hard-label black-box setting is a fundamental yet challenging problem, especially in natural language processing (NLP). The process of searching for adversarial examples has many uncertainties (e.g., an unknown impact on the target model's prediction of the added perturbation) when confidence scores cannot be accessed, which must be compensated for with a large number of queries. To address this issue, we propose TextCheater, a decision-based metaheuristic search method that performs a query-efficient textual adversarial attack task by prohibiting invalid searches. The strategies of multiple initialization points and Tabu search are also introduced to keep the search process from falling into a local optimum. We apply our approach to three state-of-the-art language models (i.e., BERT, wordLSTM, and wordCNN) across six benchmark datasets and eight real-world commercial sentiment analysis platforms/models. Furthermore, we evaluate the Robustly optimized BERT pretraining Approach (RoBERTa) and models that enhance their robustness by adversarial training on toxicity detection and text classification tasks. The results demonstrate that our method minimizes the number of queries required for crafting plausible adversarial text while outperforming existing attack methods in the attack success rate, fluency of output sentences, and similarity between the original text and its adversary.