paper-with-me

홈 › Papers

BufferSearch: Generating Black-Box Adversarial Texts With Lower Queries

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Machine learning security has recently become a prominent topic in the natural language processing (NLP) area. The existing black-box adversarial attack suffers prohibitively from the high model querying complexity, resulting in easily being captured by anti-attack monitors. Meanwhile, how to eliminate redundant model queries is rarely explored. In this paper, we propose a query-efficient approach BufferSearch to effectively attack general intelligent NLP systems with the minimal number of querying requests. In general, BufferSearch makes use of historical information and conducts statistical test to avoid incurring model queries frequently. Numerically, we demonstrate the effectiveness of BufferSearch on various benchmark text-classification experiments by achieving the competitive attacking performance but with a significant reduction of query quantity. Furthermore,BufferSearch performs multiple times better than competitors within restricted query budget. Our work establishes a strong benchmark for the future study of query-efficiency in NLP adversarial attacks. The source code is available at \url{https://tinyurl.com/buffersearch}.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Attacktext-classificationText Classification

Similar Papers 제목 키워드 기반

Generating Textual Adversaries with Minimal Perturbation

2022-11-12 · Xingyi Zhao, Lu Zhang, Depeng Xu, Shuhan Yuan

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 th…

Adversarial Attack

Heuristic Black-box Adversarial Attacks on Video Recognition Models

2019-11-21 · Zhipeng Wei, Jingjing Chen, Xingxing Wei, Linxi Jiang 외

We study the problem of attacking video recognition models in the black-box setting, where the model information is unknown and the adversary can only make queries to detect the predicted top-1 class and its probability.…

Adversarial AttackVideo Recognition

Blocking Transferability of Adversarial Examples in Black-Box Learning Systems

2017-03-13 · Hossein Hosseini, Yize Chen, Sreeram Kannan, Baosen Zhang 외

Advances in Machine Learning (ML) have led to its adoption as an integral component in many applications, including banking, medical diagnosis, and driverless cars. To further broaden the use of ML models, cloud-based se…

BlockingMedical Diagnosis

Perception Improvement for Free: Exploring Imperceptible Black-box Adversarial Attacks on Image Classification

2020-10-30 · Yongwei Wang, Mingquan Feng, Rabab Ward, Z. Jane Wang 외

Deep neural networks are vulnerable to adversarial attacks. White-box adversarial attacks can fool neural networks with small adversarial perturbations, especially for large size images. However, keeping successful adver…

Adversarial AttackGeneral Classificationimage-classificationImage Classification

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation

2025-08-14 · Huizhen Shu, Xuying Li, Qirui Wang, Yuji Kosuga 외 arxiv

With the rapid proliferation of Natural Language Processing (NLP), especially Large Language Models (LLMs), generating adversarial examples to jailbreak LLMs remains a key challenge for understanding model vulnerabilitie…

Text Generation