Enhancing Accessibility in Black-Box Attack Research with BinarySelect.pdf

Adversarial text attack research is crucial for evaluating NLP model robustness and addressing privacy concerns. However, the increasing complexity of transformer and pretrained

language models has led to significant time and resource requirements for training and testing. This challenge is particularly pronounced in black-box attacks, where hundreds

or thousands of queries may be needed to identify critical words leveraged by the target model. To overcome this, we introduce BinarySelect, a novel method combining binary search

with adversarial attack techniques to reduce query numbers significantly while maintaining attack effectiveness. Our experiments show that BinarySelect requires far fewer queries than traditional methods, making adversarial attack research more accessible to researchers with limited resources. We demonstrate the efficacy of BinarySelect across multiple datasets and classifiers, showcasing its potential for efficient adversarial attack exploration and addressing related black-box challenges.