English
Related papers

Related papers: Gradient-Based Word Substitution for Obstinate Adv…

200 papers

Adversarial attack research in natural language processing (NLP) has made significant progress in designing powerful attack methods and defence approaches. However, few efforts have sought to identify which source samples are the most…

Computation and Language · Computer Science 2023-06-26 Vyas Raina , Mark Gales

Adversarial attacks in texts are mostly substitution-based methods that replace words or characters in the original texts to achieve success attacks. Recent methods use pre-trained language models as the substitutes generator. While in…

Computation and Language · Computer Science 2021-01-01 Linyang Li , Yunfan Shao , Demin Song , Xipeng Qiu , Xuanjing Huang

The strength of modern generative models lies in their ability to be controlled through text-based prompts. Typical "hard" prompts are made from interpretable words and tokens, and must be hand-crafted by humans. There are also "soft"…

Machine Learning · Computer Science 2023-06-02 Yuxin Wen , Neel Jain , John Kirchenbauer , Micah Goldblum , Jonas Geiping , Tom Goldstein

Fine-tuning pre-trained language models (LMs) has become the de facto standard in many NLP tasks. Nevertheless, fine-tuned LMs are still prone to robustness issues, such as adversarial robustness and model calibration. Several perspectives…

Computation and Language · Computer Science 2023-12-08 Jaehyung Kim , Yuning Mao , Rui Hou , Hanchao Yu , Davis Liang , Pascale Fung , Qifan Wang , Fuli Feng , Lifu Huang , Madian Khabsa

In targeted adversarial attacks on vision models, the selection of the target label is a critical yet often overlooked determinant of attack success. This target label corresponds to the class that the attacker aims to force the model to…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Katarzyna Filus , Jorge M. Cruz-Duarte

Attacking Neural Machine Translation models is an inherently combinatorial task on discrete sequences, solved with approximate heuristics. Most methods use the gradient to attack the model on each sample independently. Instead of…

Computation and Language · Computer Science 2021-09-02 Badr Youbi Idrissi , Stéphane Clinchant

Prompt-based learning is a new language model training paradigm that adapts the Pre-trained Language Models (PLMs) to downstream tasks, which revitalizes the performance benchmarks across various natural language processing (NLP) tasks.…

Computation and Language · Computer Science 2024-04-10 Yue Xu , Wenjie Wang

Language models (LMs) are indispensable tools for natural language processing tasks, but their vulnerability to adversarial attacks remains a concern. While current research has explored adversarial training techniques, their improvements…

Computation and Language · Computer Science 2024-03-28 Brian Formento , Wenjie Feng , Chuan Sheng Foo , Luu Anh Tuan , See-Kiong Ng

To circumvent the alignment of large language models (LLMs), current optimization-based adversarial attacks usually craft adversarial prompts by maximizing the likelihood of a so-called affirmative response. An affirmative response is a…

Deep neural networks are vulnerable to adversarial attacks, where a small perturbation to an input alters the model prediction. In many cases, malicious inputs intentionally crafted for one model can fool another model. In this paper, we…

Machine Learning · Computer Science 2021-09-23 Liping Yuan , Xiaoqing Zheng , Yi Zhou , Cho-Jui Hsieh , Kai-wei Chang

Recently proposed Skip-gram model is a powerful method for learning high-dimensional word representations that capture rich semantic relationships between words. However, Skip-gram as well as most prior work on learning word representations…

Computation and Language · Computer Science 2015-11-17 Sergey Bartunov , Dmitry Kondrashkin , Anton Osokin , Dmitry Vetrov

We propose a generative model for adversarial attack. The model generates subtle but predictive patterns from the input. To perform an attack, it replaces the patterns of the input with those generated based on examples from some other…

Machine Learning · Computer Science 2019-12-02 Ziang Dong , Liang Mao , Shiliang Sun

Recent advances in large language models have highlighted the critical need for precise control over model outputs through predefined constraints. While existing methods attempt to achieve this through either direct instruction-response…

Computation and Language · Computer Science 2025-03-27 Zhouhong Gu , Xingzhou Chen , Xiaoran Shi , Tao Wang , Suhang Zheng , Tianyu Li , Hongwei Feng , Yanghua Xiao

Insensitivity to semantically-preserving variations of prompts (paraphrases) is crucial for reliable behavior and real-world deployment of large language models. However, language models exhibit significant performance degradation when…

Computation and Language · Computer Science 2025-03-04 Tingchen Fu , Fazl Barez

Adversarial training is a training scheme designed to counter adversarial attacks by augmenting the training dataset with adversarial examples. Surprisingly, several studies have observed that loss gradients from adversarially trained DNNs…

Machine Learning · Computer Science 2019-04-22 Beomsu Kim , Junghoon Seo , Taegyun Jeon

Deep neural networks are vulnerable to adversarial examples, which are crafted by adding human-imperceptible perturbations to original images. Most existing adversarial attack methods achieve nearly 100% attack success rates under the…

Computer Vision and Pattern Recognition · Computer Science 2022-04-15 Guoqiu Wang , Huanqian Yan , Ying Guo , Xingxing Wei

Adversarial samples for images have been extensively studied in the literature. Among many of the attacking methods, gradient-based methods are both effective and easy to compute. In this work, we propose a framework to adapt the gradient…

Computation and Language · Computer Science 2018-01-26 Zhitao Gong , Wenlu Wang , Bo Li , Dawn Song , Wei-Shinn Ku

Transformer-based language models significantly advanced the state-of-the-art in many linguistic tasks. As this revolution continues, the ability to explain model predictions has become a major area of interest for the NLP community. In…

Machine Learning · Computer Science 2022-04-26 Oren Barkan , Edan Hauon , Avi Caciularu , Ori Katz , Itzik Malkiel , Omri Armstrong , Noam Koenigstein

Currently, natural language processing (NLP) models are wildly used in various scenarios. However, NLP models, like all deep models, are vulnerable to adversarially generated text. Numerous works have been working on mitigating the…

Computation and Language · Computer Science 2023-02-14 Lujia Shen , Xuhong Zhang , Shouling Ji , Yuwen Pu , Chunpeng Ge , Xing Yang , Yanghe Feng

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