paper-with-me

홈 › Papers

Certified Robustness to Word Substitution Ranking Attack for Neural Ranking Models

2022-09-14 · Chen Wu, Ruqing Zhang, Jiafeng Guo, Wei Chen, Yixing Fan, Maarten de Rijke, Xueqi Cheng

Neural ranking models (NRMs) have achieved promising results in information retrieval. NRMs have also been shown to be vulnerable to adversarial examples. A typical Word Substitution Ranking Attack (WSRA) against NRMs was proposed recently, in which an attacker promotes a target document in rankings by adding human-imperceptible perturbations to its text. This raises concerns when deploying NRMs in real-world applications. Therefore, it is important to develop techniques that defend against such attacks for NRMs. In empirical defenses adversarial examples are found during training and used to augment the training set. However, such methods offer no theoretical guarantee on the models' robustness and may eventually be broken by other sophisticated WSRAs. To escape this arms race, rigorous and provable certified defense methods for NRMs are needed. To this end, we first define the \textit{Certified Top-$K$ Robustness} for ranking models since users mainly care about the top ranked results in real-world scenarios. A ranking model is said to be Certified Top-$K$ Robust on a ranked list when it is guaranteed to keep documents that are out of the top $K$ away from the top $K$ under any attack. Then, we introduce a Certified Defense method, named CertDR, to achieve certified top-$K$ robustness against WSRA, based on the idea of randomized smoothing. Specifically, we first construct a smoothed ranker by applying random word substitutions on the documents, and then leverage the ranking property jointly with the statistical property of the ensemble to provably certify top-$K$ robustness. Extensive experiments on two representative web search datasets demonstrate that CertDR can significantly outperform state-of-the-art empirical defense methods for ranking models.

📄 PDF Abstract BibTeX arXiv:2209.06691

Code (1)

ict-bigdatalab/certdr 공식 구현 pytorch

Tasks

Information RetrievalRetrieval

Similar Papers 제목 키워드 기반

Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks

2023-07-31 · Xinyu Zhang, Hanbin Hong, Yuan Hong, Peng Huang 외

The language models, especially the basic text classification models, have been shown to be susceptible to textual adversarial attacks such as synonym substitution and word insertion attacks. To defend against such attac…

text-classificationText Classification

Certified Robustness to Word Substitution Attack with Differential Privacy

2021-06-01 · NAACL 2021 4 · Wenjie Wang, Pengfei Tang, Jian Lou, Li Xiong

The robustness and security of natural language processing (NLP) models are significantly important in real-world applications. In the context of text classification tasks, adversarial examples can be designed by substit…

Adversarial RobustnessClassificationtext-classificationText Classification

S-GBT: Smooth Growth Bound Tensor for Certified Robustness Against Word Substitution Attacks in NLP

2026-06-11 · Mohammed Bouri, Mohammed Erradi, Adnane Saoud arxiv

Despite recent progress in Natural Language Processing (NLP), models remain vulnerable to word substitution attacks. Most existing defenses focus on first order sensitivity and measure how much the output changes when th…

Certified Robustness to Text Adversarial Attacks by Randomized [MASK]

2021-05-08 · Jiehang Zeng, Xiaoqing Zheng, Jianhan Xu, Linyang Li 외

Recently, few certified defense methods have been developed to provably guarantee the robustness of a text classifier to adversarial synonym substitutions. However, all existing certified defense methods assume that the …

Certified Robustness Against Natural Language Attacks by Causal Intervention

2022-05-24 · Haiteng Zhao, Chang Ma, Xinshuai Dong, Anh Tuan Luu 외

Deep learning models have achieved great success in many fields, yet they are vulnerable to adversarial examples. This paper follows a causal perspective to look into the adversarial vulnerability and proposes Causal Int…