相关论文: Adversarial Subword Regularization for Robust Neur…

While it has been shown that Neural Machine Translation (NMT) is highly sensitive to noisy parallel training samples, prior work treats all types of mismatches between source and target as noise. As a result, it remains unclear how samples…

Adversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the training process. Recent studies have demonstrated the…

Neural networks are vulnerable to adversarial attacks: adding well-crafted, imperceptible perturbations to their input can modify their output. Adversarial training is one of the most effective approaches to training robust models against…

Transfer learning approaches for Neural Machine Translation (NMT) train a NMT model on the assisting-target language pair (parent model) which is later fine-tuned for the source-target language pair of interest (child model), with the…

While end-to-end neural machine translation (NMT) has achieved impressive progress, noisy input usually leads models to become fragile and unstable. Generating adversarial examples as the augmented data has been proved to be useful to…

Recent studies imply that deep neural networks are vulnerable to adversarial examples -- inputs with a slight but intentional perturbation are incorrectly classified by the network. Such vulnerability makes it risky for some…

Neural Machine Translation (NMT) models have been proved strong when translating clean texts, but they are very sensitive to noise in the input. Improving NMT models robustness can be seen as a form of "domain" adaption to noise. The…

Pre-trained contextualized language models (PrLMs) have led to strong performance gains in downstream natural language understanding tasks. However, PrLMs can still be easily fooled by adversarial word substitution, which is one of the most…

With the increasing deployment of automated and agentic systems, ensuring the adversarial robustness of automatic speech recognition (ASR) models has become critical. We observe that changing the precision of an ASR model during inference…

Given the widespread use of deep learning models in safety-critical applications, ensuring that the decisions of such models are robust against adversarial exploitation is of fundamental importance. In this thesis, we discuss recent…

Recent empirical studies show that adversarial topic models (ATM) can successfully capture semantic patterns of the document by differentiating a document with another dissimilar sample. However, utilizing that discriminative-generative…

Adversarial training (AT) as a regularization method has proved its effectiveness on various tasks. Though there are successful applications of AT on some NLP tasks, the distinguishing characteristics of NLP tasks have not been exploited.…

Given the great success of Deep Neural Networks(DNNs) and the black-box nature of it,the interpretability of these models becomes an important issue.The majority of previous research works on the post-hoc interpretation of a trained…

Adversarial training often suffers from a robustness-accuracy trade-off, where achieving high robustness comes at the cost of accuracy. One approach to mitigate this trade-off is leveraging invariance regularization, which encourages model…

Improving the resistance of deep neural networks against adversarial attacks is important for deploying models to realistic applications. However, most defense methods are designed to defend against intensity perturbations and ignore…

Deep neural networks (DNNs) are vulnerable to adversarial examples where inputs with imperceptible perturbations mislead DNNs to incorrect results. Despite the potential risk they bring, adversarial examples are also valuable for providing…

Adversarial training, which minimizes the maximal risk for label-preserving input perturbations, has proved to be effective for improving the generalization of language models. In this work, we propose a novel adversarial training…

Adversarial examples derived from deliberately crafted perturbations on visual inputs can easily harm decision process of deep neural networks. To prevent potential threats, various adversarial training-based defense methods have grown…

Generative Adversarial Networks (GAN) offer a promising approach for Neural Machine Translation (NMT). However, feeding multiple morphologically languages into a single model during training reduces the NMT's performance. In GAN, similar to…

Reward modeling has emerged as a promising approach for the scalable alignment of language models. However, contemporary reward models (RMs) often lack robustness, awarding high rewards to low-quality, out-of-distribution (OOD) samples.…