We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Adversarial attacks against machine learning models have threatened various real-world applications such as spam filtering and sentiment analysis. In this paper, we propose a novel framework, learning to DIScriminate Perturbations (DISP), to identify and adjust malicious perturbations, thereby blocking adversarial attacks for text classification models. To identify adversarial attacks, a perturbation discriminator validates how likely a token in the text is perturbed and provides a set of potential perturbations. For each potential perturbation, an embedding estimator learns to restore the embedding of the original word based on the context and a replacement token is chosen based on approximate kNN search. DISP can block adversarial attacks for any NLP model without modifying the model structure or training procedure. Extensive experiments on two benchmark datasets demonstrate that DISP significantly outperforms baseline methods in blocking adversarial attacks for text classification. In addition, in-depth analysis shows the robustness of DISP across different situations.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1909.03084")
get_code_for_paper("1909.03084")
have("1909.03084")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1909.03084.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1909.03084)
Connect an agent — have() is free.