paper-with-me

Papers

Text Adversarial Attacks with Dynamic Outputs

2025-09-26 · Wenqiang Wang, Siyuan Liang, Xiao Yan, Xiaochun Cao arxiv

Text adversarial attack methods are typically designed for static scenarios with fixed numbers of output labels and a predefined label space, relying on extensive querying of the victim model (query-based attacks) or the surrogate model (transfer-based attacks). To address this gap, we introduce the Textual Dynamic Outputs Attack (TDOA) method, which employs a clustering-based surrogate model training approach to convert the dynamic-output scenario into a static single-output scenario. To improve attack effectiveness, we propose the farthest-label targeted attack strategy, which selects adversarial vectors that deviate most from the model's coarse-grained labels, thereby maximizing disruption. We extensively evaluate TDOA on four datasets and eight victim models (e.g., ChatGPT-4o, ChatGPT-4.1), showing its effectiveness in crafting adversarial examples and its strong potential to compromise large language models with limited access. With a single query per text, TDOA achieves a maximum attack success rate of 50.81\%. Additionally, we find that TDOA also achieves state-of-the-art performance in conventional static output scenarios, reaching a maximum ASR of 82.68\%. Meanwhile, by conceptualizing translation tasks as classification problems with unbounded output spaces, we extend the TDOA framework to generative settings, surpassing prior results by up to 0.64 RDBLEU and 0.62 RDchrF.

📄 PDF Abstract BibTeX arXiv:2509.22393

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Attack

Similar Papers 제목 키워드 기반

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models

2025-08-26 · Rui Zhang, Zihan Wang, Tianli Yang, Hongwei Li 외 arxiv

Vision-Language Models (VLMs) are increasingly deployed in real-world applications, but their high inference cost makes them vulnerable to resource consumption attacks. Prior attacks attempt to extend VLM output sequence…

Adversarial Attacks on Remote User Authentication Using Behavioural Mouse Dynamics

2019-05-28 · Yi Xiang Marcus Tan, Alfonso Iacovazzi, Ivan Homoliak, Yuval Elovici 외

Mouse dynamics is a potential means of authenticating users. Typically, the authentication process is based on classical machine learning techniques, but recently, deep learning techniques have been introduced for this p…

BIG-bench Machine Learning

Improving Alignment and Robustness with Circuit Breakers

2024-06-06 · Andy Zou, Long Phan, Justin Wang, Derek Duenas 외

AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that interrupts the models as they respond with har…

Adversarial Robustness

When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse

2026-08-07 · Yingtao Ren, Ziyi Zhao, Yiwei Fu, Xiao Luo 외 hf

Retrieval-augmented generation (RAG) is indispensable for enhancing large language models. However, RAGs are increasingly susceptible to poisoning attacks, in which adversarial documents are injected to manipulate genera…

Robustness Against Adversarial Attacks via Learning Confined Adversarial Polytopes

2024-01-15 · Shayan Mohajer Hamidi, Linfeng Ye

Deep neural networks (DNNs) could be deceived by generating human-imperceptible perturbations of clean samples. Therefore, enhancing the robustness of DNNs against adversarial attacks is a crucial task. In this paper, we…

Adversarial Robustness