“Gradient-Based Adversarial Attacks against Text Transformers”, 2021-04-15 (; similar):
We propose the first general-purpose gradient-based attack against transformer models.
Instead of searching for a single adversarial example, we search for a distribution of adversarial examples parameterized by a continuous-valued matrix, hence enabling gradient-based optimization.
We empirically demonstrate that our white-box attack attains state-of-the-art attack performance on a variety of natural language tasks.
Furthermore, we show that a powerful black-box transfer attack, enabled by sampling from the adversarial distribution, matches or exceeds existing methods, while only requiring hard-label outputs.