Grey-box Adversarial Attack And Defence For Sentiment Classification

Xu, Ying; Zhong, Xu; Yepes, Antonio Jimeno; Lau, Jey Han

doi:10.48550/arxiv.2103.11576

Cited by 8 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They used FGSM to produce perturbations in word embedding and used nearest neighbor search to find the closest words. However, this approach treated all tokens as equally vulnerable and replace all tokens with their nearest neighbors, which led to non-sensical, word-salad outputs [76]. A number of works [32,33,42,62] utilized the ideas of JSMA (e.g., find important pixel) to solve this problem.…”

Section: Adversarial Operationmentioning

confidence: 99%

Are Neural Ranking Models Robust?

Chen¹,

Zhang²,

Guo³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recently, we have witnessed the bloom of neural ranking models in the information retrieval (IR) field. So far, much effort has been devoted to developing effective neural ranking models that can generalize well on new data. There has been less attention paid to the robustness perspective. Unlike the effectiveness which is about the average performance of a system under normal purpose, robustness cares more about the system performance in the worst case or under malicious operations instead. When a new technique enters into the real-world application, it is critical to know not only how it works in average, but also how would it behave in abnormal situations. So we raise the question in this work: Are neural ranking models robust? To answer this question, firstly, we need to clarify what we refer to when we talk about the robustness of ranking models in IR. We show that robustness is actually a multi-dimensional concept and there are three ways to define it in IR: 1) The performance variance under the independent and identically distributed (I.I.D.) setting; 2) The out-of-distribution (OOD) generalizability; and 3) The defensive ability against adversarial operations. The latter two definitions can be further specified into two different perspectives respectively, leading to 5 robustness tasks in total. Based on this taxonomy, we build corresponding benchmark datasets, design empirical experiments, and systematically analyze the robustness of several representative neural ranking models against traditional probabilistic ranking models and learning-to-rank (LTR) models. The empirical results show that there is no simple answer to our question. While neural ranking models are less robust against other IR models in most cases, some of them can still win 1 out of 5 tasks. This is the first comprehensive study on the robustness of neural ranking models. We believe the way we study the robustness as well as our findings would be beneficial to the IR community. We will also release all the data and codes to facilitate the future research in this direction.CCS Concepts: • Information systems → Retrieval models and ranking.

show abstract

Section: Adversarial Operationmentioning

confidence: 99%

Are Neural Ranking Models Robust?

Chen¹,

Zhang²,

Guo³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In the white-box approach, the target model is known to the adversary. In a blackbox approach, the target model is not known whereas, in a grey-box attack, an adversary is assumed to know the architecture of the target model, but have no access to the weights in the network [24,25]. Among these attacks, the white-box attack is generally the strongest form of attack.…”

Section: Adversarial Attacksmentioning

confidence: 99%

An anti-attack method for emotion categorization from images

Shehu

Browne

Eisenbarth

2022

Applied Soft Computing

View full text Add to dashboard Cite

“…All the above discussed methods used the generated adversarial examples for the adversarial training in order to defend the model from attacks and increase robustness. In [120] authors proposed a grey box adversarial attack with the help of a generator model for sentiment analysis task. Adversarial training is done augmenting the data using a static copy mask mechanism in generator, where data is augmented only at the positions which are not masked.…”

Section: Adversarial Training Based Defensesmentioning

confidence: 99%

A survey in Adversarial Defences and Robustness in NLP

Goyal¹,

Doddapaneni²,

Khapra³

et al. 2022

Preprint

View full text Add to dashboard Cite

In recent years, it has been seen that deep neural networks are lacking robustness and are likely to break in case of adversarial perturbations in input data. Strong adversarial attacks are proposed by various authors for computer vision and Natural Language Processing (NLP). As a counter-effort, several defense mechanisms are also proposed to save these networks from failing. In contrast with image data, generating adversarial attacks and defending these models is not easy in NLP because of the discrete nature of the text data. However, numerous methods for adversarial defense are proposed of late, for different NLP tasks such as text classification, named entity recognition, natural language inferencing, etc. These methods are not just used for defending neural networks from adversarial attacks, but also used as a regularization mechanism during training, saving the model from overfitting. The proposed survey is an attempt to review different methods proposed for adversarial defenses in NLP in the recent past by proposing a novel taxonomy. This survey also highlights the fragility of the advanced deep neural networks in NLP and the challenges in defending them.

show abstract

Grey-box Adversarial Attack And Defence For Sentiment Classification

Cited by 8 publications

References 26 publications

Are Neural Ranking Models Robust?

Are Neural Ranking Models Robust?

An anti-attack method for emotion categorization from images

A survey in Adversarial Defences and Robustness in NLP

Contact Info

Product

Resources

About