Papers with adversarial perturbation
Effective Adversarial Regularization for Neural Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Existing (small) perturbations that induce a critical prediction error in machine learning models are often referred to as adversarial examples. |
| Approach: | They propose to use adversarial perturbations to regularize text classification tasks by adding adversarials to a typical NMT model structure. |
| Outcome: | The proposed method significantly improves performance of NMT models, such as LSTM-based and Transformer-based models. |
Semi-supervised Adversarial Text Generation based on Seq2Seq models (2022.emnlp-industry)
Copied to clipboard
| Challenge: | In contrast, adversarial training has been used in computer vision to improve models’ robustness due to the discrete nature of text. |
| Approach: | They propose a way to generate adversarial samples by using pseudo-labeled in-domain text data to train a seq2seq model for adversarials and combine it with paraphrase detection. |
| Outcome: | The proposed model generates realistic and relevant adversarial samples compared to other state-of-the-art models and recovers up to 70% of errors. |
TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attack (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing textual adversarial attacks use gradient or prediction confidence to generate adversarials, making it hard to be deployed in real-world applications. |
| Approach: | They propose a textual adversarial attack that randomly perturbs lots of words to craft an adversarial example. |
| Outcome: | The proposed attack outperforms existing hard-label attacks in terms of attack performance and adversary quality. |
On the Robustness of Self-Attentive Models (P19-1)
Copied to clipboard
| Challenge: | Experimental results show that self-attentive neural models are more robust against adversarial perturbations compared to recurrent neural networks. |
| Approach: | They propose an adversarial attack algorithm that generates more natural adversarials . they propose to use the attention mechanism to learn a context-dependent representation . |
| Outcome: | The proposed attack algorithm generates more natural adversarial examples that could mislead models but not humans. |
RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training (2023.findings-emnlp)
Copied to clipboard
Jaehyung Kim, Yuning Mao, Rui Hou, Hanchao Yu, Davis Liang, Pascale Fung, Qifan Wang, Fuli Feng, Lifu Huang, Madian Khabsa
| Challenge: | Several perspectives of robustness for pre-trained language models have been studied independently, but lacking a unified consideration in multiple perspectives. |
| Approach: | They propose a technique to enhance the multi-perspective robustness of LMs by introducing adversarial perturbation while the model parameters are selectively updated upon their relative importance. |
| Outcome: | The proposed technique improves the robustness of LMs by incorporating four perspectives on model robustness. |
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing adversarial examples can induce arbitrary errors to the target models, but they can be exploited to estimate robustness of NLP models. |
| Approach: | They propose a target-controllable adversarial attack framework T3 to handle adversarials . they use tree-based decoders to regularize the syntactic correctness of generated text . |
| Outcome: | The proposed framework can be used to estimate the robustness of NLP models. |
Attention-Focused Adversarial Training for Robust Temporal Reasoning (2022.lrec-1)
Copied to clipboard
| Challenge: | Current adversarial training approaches for NLP add adversarials to the embedding layer, ignoring other layers. |
| Approach: | They propose an enhanced adversarial training algorithm for fine-tuning transformer-based language models . they add the adversarials to multiple hidden states or attention representations of the model layers . |
| Outcome: | The proposed model improves performance on several temporal reasoning benchmarks and establishes new state-of-the-art results. |