paper-with-me

Papers

Frauds Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process

2023-03-01 · Mingze Ni, Zhensu Sun, Wei Liu

Recent research has revealed that natural language processing (NLP) models are vulnerable to adversarial examples. However, the current techniques for generating such examples rely on deterministic heuristic rules, which fail to produce optimal adversarial examples. In response, this study proposes a new method called the Fraud's Bargain Attack (FBA), which uses a randomization mechanism to expand the search space and produce high-quality adversarial examples with a higher probability of success. FBA uses the Metropolis-Hasting sampler, a type of Markov Chain Monte Carlo sampler, to improve the selection of adversarial examples from all candidates generated by a customized stochastic process called the Word Manipulation Process (WMP). The WMP method modifies individual words in a contextually-aware manner through insertion, removal, or substitution. Through extensive experiments, this study demonstrates that FBA outperforms other methods in terms of attack success rate, imperceptibility and sentence quality.

📄 PDF Abstract BibTeX arXiv:2303.01234

Code (1)

mingzelucasni/fba 공식 구현 pytorch

Tasks

Adversarial TextSentence

Similar Papers 제목 키워드 기반

Graph-Fraudster: Adversarial Attacks on Graph Neural Network Based Vertical Federated Learning

2021-10-13 · Jinyin Chen, Guohan Huang, Haibin Zheng, Shanqing Yu 외

Graph neural network (GNN) has achieved great success on graph representation learning. Challenged by large scale private data collected from user-side, GNN may not be able to reflect the excellent performance, without r…

Adversarial AttackFederated LearningGraph Neural NetworkGraph Representation Learning+2

Towards Adversarially Robust Recommendation from Adaptive Fraudster Detection

2022-11-08 · Yuni Lai, Yulin Zhu, Wenqi Fan, Xiaoge Zhang 외

The robustness of recommender systems under node injection attacks has garnered significant attention. Recently, GraphRfi, a GNN-based recommender system, was proposed and shown to effectively mitigate the impact of inje…

Adversarial RobustnessRecommendation Systems

Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methods

2024-04-08 · Roopkatha Dey, Aivy Debnath, Sayak Kumar Dutta, Kaustav Ghosh 외

In various real-world applications such as machine translation, sentiment analysis, and question answering, a pivotal role is played by NLP models, facilitating efficient communication and decision-making processes in do…

Adversarial TextMachine TranslationQuestion AnsweringSemantic Similarity+4

A General Black-box Adversarial Attack on Graph-based Fake News Detectors

2024-04-24 · Peican Zhu, Zechen Pan, Yang Liu, Jiwei Tian 외

Graph Neural Network (GNN)-based fake news detectors apply various methods to construct graphs, aiming to learn distinctive news embeddings for classification. Since the construction details are unknown for attackers in …

Adversarial AttackGraph Neural Network

Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets

2023-06-27 · CVPR 2023 1 · Yimu Wang, Dinghuai Zhang, Yihan Wu, Heng Huang 외

Despite incredible advances, deep learning has been shown to be susceptible to adversarial attacks. Numerous approaches have been proposed to train robust networks both empirically and certifiably. However, most of them …