Adversarial Augmentation Policy Search for Domain and Cross-Lingual
Generalization in Reading Comprehension
- URL: http://arxiv.org/abs/2004.06076v4
- Date: Tue, 17 Nov 2020 16:43:56 GMT
- Title: Adversarial Augmentation Policy Search for Domain and Cross-Lingual
Generalization in Reading Comprehension
- Authors: Adyasha Maharana, Mohit Bansal
- Abstract summary: Reading comprehension models often overfit to nuances of training datasets and fail at adversarial evaluation.
We present several effective adversaries and automated data augmentation policy search methods with the goal of making reading comprehension models more robust to adversarial evaluation.
- Score: 96.62963688510035
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Reading comprehension models often overfit to nuances of training datasets
and fail at adversarial evaluation. Training with adversarially augmented
dataset improves robustness against those adversarial attacks but hurts
generalization of the models. In this work, we present several effective
adversaries and automated data augmentation policy search methods with the goal
of making reading comprehension models more robust to adversarial evaluation,
but also improving generalization to the source domain as well as new domains
and languages. We first propose three new methods for generating QA
adversaries, that introduce multiple points of confusion within the context,
show dependence on insertion location of the distractor, and reveal the
compounding effect of mixing adversarial strategies with syntactic and semantic
paraphrasing methods. Next, we find that augmenting the training datasets with
uniformly sampled adversaries improves robustness to the adversarial attacks
but leads to decline in performance on the original unaugmented dataset. We
address this issue via RL and more efficient Bayesian policy search methods for
automatically learning the best augmentation policy combinations of the
transformation probability for each adversary in a large search space. Using
these learned policies, we show that adversarial training can lead to
significant improvements in in-domain, out-of-domain, and cross-lingual
(German, Russian, Turkish) generalization.
Related papers
- Efficient Adversarial Training in LLMs with Continuous Attacks [99.5882845458567]
Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails.
We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses.
C-AdvIPO is an adversarial variant of IPO that does not require utility data for adversarially robust alignment.
arXiv Detail & Related papers (2024-05-24T14:20:09Z) - READ: Improving Relation Extraction from an ADversarial Perspective [33.44949503459933]
We propose an adversarial training method specifically designed for relation extraction (RE)
Our approach introduces both sequence- and token-level perturbations to the sample and uses a separate perturbation vocabulary to improve the search for entity and context perturbations.
arXiv Detail & Related papers (2024-04-02T16:42:44Z) - Mutual-modality Adversarial Attack with Semantic Perturbation [81.66172089175346]
We propose a novel approach that generates adversarial attacks in a mutual-modality optimization scheme.
Our approach outperforms state-of-the-art attack methods and can be readily deployed as a plug-and-play solution.
arXiv Detail & Related papers (2023-12-20T05:06:01Z) - Combating Exacerbated Heterogeneity for Robust Models in Federated
Learning [91.88122934924435]
Combination of adversarial training and federated learning can lead to the undesired robustness deterioration.
We propose a novel framework called Slack Federated Adversarial Training (SFAT)
We verify the rationality and effectiveness of SFAT on various benchmarked and real-world datasets.
arXiv Detail & Related papers (2023-03-01T06:16:15Z) - Model-Agnostic Meta-Attack: Towards Reliable Evaluation of Adversarial
Robustness [53.094682754683255]
We propose a Model-Agnostic Meta-Attack (MAMA) approach to discover stronger attack algorithms automatically.
Our method learns the in adversarial attacks parameterized by a recurrent neural network.
We develop a model-agnostic training algorithm to improve the ability of the learned when attacking unseen defenses.
arXiv Detail & Related papers (2021-10-13T13:54:24Z) - Delving into Data: Effectively Substitute Training for Black-box Attack [84.85798059317963]
We propose a novel perspective substitute training that focuses on designing the distribution of data used in the knowledge stealing process.
The combination of these two modules can further boost the consistency of the substitute model and target model, which greatly improves the effectiveness of adversarial attack.
arXiv Detail & Related papers (2021-04-26T07:26:29Z) - Multi-Task Federated Reinforcement Learning with Adversaries [2.6080102941802106]
Reinforcement learning algorithms pose a serious threat from adversaries.
In this paper, we analyze the Multi-task Federated Reinforcement Learning algorithms.
We propose an adaptive attack method with better attack performance.
arXiv Detail & Related papers (2021-03-11T05:39:52Z) - Improving adversarial robustness of deep neural networks by using
semantic information [17.887586209038968]
Adrial training is the main method for improving adversarial robustness and the first line of defense against adversarial attacks.
This paper provides a new perspective on the issue of adversarial robustness, one that shifts the focus from the network as a whole to the critical part of the region close to the decision boundary corresponding to a given class.
Experimental results on the MNIST and CIFAR-10 datasets show that this approach greatly improves adversarial robustness even using a very small dataset from the training data.
arXiv Detail & Related papers (2020-08-18T10:23:57Z) - Class-Aware Domain Adaptation for Improving Adversarial Robustness [27.24720754239852]
adversarial training has been proposed to train networks by injecting adversarial examples into the training data.
We propose a novel Class-Aware Domain Adaptation (CADA) method for adversarial defense without directly applying adversarial training.
arXiv Detail & Related papers (2020-05-10T03:45:19Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.