English
Related papers

Related papers: Reevaluating Adversarial Examples in Natural Langu…

200 papers

Generating adversarial examples for natural language is hard, as natural language consists of discrete symbols, and examples are often of variable lengths. In this paper, we propose a geometry-inspired attack for generating natural language…

Computation and Language · Computer Science 2020-10-06 Zhao Meng , Roger Wattenhofer

Deep learning based systems are susceptible to adversarial attacks, where a small, imperceptible change at the input alters the model prediction. However, to date the majority of the approaches to detect these attacks have been designed for…

Computation and Language · Computer Science 2022-09-27 Vyas Raina , Mark Gales

Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial…

Many word-level adversarial attack approaches for textual data have been proposed in recent studies. However, due to the massive search space consisting of combinations of candidate words, the existing approaches face the problem of…

Computation and Language · Computer Science 2022-11-15 Xingyi Zhao , Lu Zhang , Depeng Xu , Shuhan Yuan

Over the past few years, various word-level textual attack approaches have been proposed to reveal the vulnerability of deep neural networks used in natural language processing. Typically, these approaches involve an important optimization…

Computation and Language · Computer Science 2021-11-23 Shengcai Liu , Ning Lu , Cheng Chen , Ke Tang

Traditional (fickle) adversarial examples involve finding a small perturbation that does not change an input's true label but confuses the classifier into outputting a different prediction. Conversely, obstinate adversarial examples occur…

Computation and Language · Computer Science 2022-11-01 Hannah Chen , Yangfeng Ji , David Evans

Adversarial examples are inputs to machine learning models designed to cause the model to make a mistake. They are useful for understanding the shortcomings of machine learning models, interpreting their results, and for regularisation. In…

Machine Learning · Computer Science 2018-08-28 Pasquale Minervini , Sebastian Riedel

Real-world natural language processing systems need to be robust to human adversaries. Collecting examples of human adversaries for training is an effective but expensive solution. On the other hand, training on synthetic attacks with small…

Machine Learning · Computer Science 2024-02-16 Aradhana Sinha , Ananth Balashankar , Ahmad Beirami , Thi Avrahami , Jilin Chen , Alex Beutel

Neural networks are part of many contemporary NLP systems, yet their empirical successes come at the price of vulnerability to adversarial attacks. Previous work has used adversarial training and data augmentation to partially mitigate such…

Computation and Language · Computer Science 2019-12-23 Po-Sen Huang , Robert Stanforth , Johannes Welbl , Chris Dyer , Dani Yogatama , Sven Gowal , Krishnamurthy Dvijotham , Pushmeet Kohli

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

Computation and Language · Computer Science 2022-08-23 Jiayi Wang , Rongzhou Bao , Zhuosheng Zhang , Hai Zhao

In recent years, large pre-trained language models (PLMs) have achieved remarkable performance on many natural language processing benchmarks. Despite their success, prior studies have shown that PLMs are vulnerable to attacks from…

Computation and Language · Computer Science 2024-02-06 Shuguang Chen , Leonardo Neves , Thamar Solorio

An adversarial attack paradigm explores various scenarios for the vulnerability of deep learning models: minor changes of the input can force a model failure. Most of the state of the art frameworks focus on adversarial attacks for images…

Machine Learning · Computer Science 2020-06-22 I. Fursov , A. Zaytsev , N. Kluchnikov , A. Kravchenko , E. Burnaev

Large language models are now tuned to align with the goals of their creators, namely to be "helpful and harmless." These models should respond helpfully to user questions, but refuse to answer requests that could cause harm. However,…

Adversarial attacks and backdoor attacks are two common security threats that hang over deep learning. Both of them harness task-irrelevant features of data in their implementation. Text style is a feature that is naturally irrelevant to…

Computation and Language · Computer Science 2021-10-15 Fanchao Qi , Yangyi Chen , Xurui Zhang , Mukai Li , Zhiyuan Liu , Maosong Sun

Deep neural networks have been shown to be vulnerable to adversarial examples deliberately constructed to misclassify victim models. As most adversarial examples have restricted their perturbations to $L_{p}$-norm, existing defense methods…

Computer Vision and Pattern Recognition · Computer Science 2021-03-16 Hanieh Naderi , Leili Goli , Shohreh Kasaei

Recent studies show that neural natural language processing (NLP) models are vulnerable to backdoor attacks. Injected with backdoors, models perform normally on benign examples but produce attacker-specified predictions when the backdoor is…

Computation and Language · Computer Science 2021-06-14 Fanchao Qi , Yuan Yao , Sophia Xu , Zhiyuan Liu , Maosong Sun

Neural Machine Translation (NMT) systems are used in various applications. However, it has been shown that they are vulnerable to very small perturbations of their inputs, known as adversarial attacks. In this paper, we propose a new…

Computation and Language · Computer Science 2023-03-03 Sahar Sadrizadeh , AmirHossein Dabiri Aghdam , Ljiljana Dolamic , Pascal Frossard

Large-scale language models achieved state-of-the-art performance over a number of language tasks. However, they fail on adversarial language examples, which are sentences optimized to fool the language models but with similar semantic…

Computation and Language · Computer Science 2023-10-31 Noah Thomas McDermott , Junfeng Yang , Chengzhi Mao

Recently, advanced NLP models have seen a surge in the usage of various applications. This raises the security threats of the released models. In addition to the clean models' unintentional weaknesses, {\em i.e.,} adversarial attacks, the…

Computation and Language · Computer Science 2021-01-18 Lichao Sun

Recent studies have shown that deep neural networks are vulnerable to intentionally crafted adversarial examples, and various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models. However,…

Computation and Language · Computer Science 2021-10-07 Zongyi Li , Jianhan Xu , Jiehang Zeng , Linyang Li , Xiaoqing Zheng , Qi Zhang , Kai-Wei Chang , Cho-Jui Hsieh