Many word-level adversarial attack approaches for textual data have been proposed in recent studies. However, due to the massive search space consisting of combinations of candidate words, the existing approaches face the problem of preserving the semantics of texts when crafting adversarial counterparts. In this paper, we develop a novel attack strategy to find adversarial texts with high similarity to the original texts while introducing minimal perturbation. The rationale is that we expect the adversarial texts with small perturbation can better preserve the semantic meaning of original texts. Experiments show that, compared with state-of-the-art attack approaches, our approach achieves higher success rates and lower perturbation rates in four benchmark datasets.

Plants have memories of past events that they can pass onto their offspring. For instance, 'mother' plants can sense temperature changes and use that information to form long-term memories that help future generation flower at the right time. Now, new research has found a prions, a protein linked to mad cow disease, could be responsible for how plants form memories. Plants have memories of past events that they can pass onto their offspring. Prions are a type of protein that fold under certain conditions. They can also trigger other proteins around them to fold as well.