paper-with-me

홈 › Papers

Dashed Line Defense: Plug-And-Play Defense Against Adaptive Score-Based Query Attacks

2026-02-09 · Yanzhang Fu, Zizheng Guo, Jizhou Luo arxiv

Score-based query attacks pose a serious threat to deep learning models by crafting adversarial examples (AEs) using only black-box access to model output scores, iteratively optimizing inputs based on observed loss values. While recent runtime defenses attempt to disrupt this process via output perturbation, most either require access to model parameters or fail when attackers adapt their tactics. In this paper, we first reveal that even the state-of-the-art plug-and-play defense can be bypassed by adaptive attacks, exposing a critical limitation of existing runtime defenses. We then propose Dashed Line Defense (DLD), a plug-and-play post-processing method specifically designed to withstand adaptive query strategies. By introducing ambiguity in how the observed loss reflects the true adversarial strength of candidate examples, DLD prevents attackers from reliably analyzing and adapting their queries, effectively disrupting the AE generation process. We provide theoretical guarantees of DLD's defense capability and validate its effectiveness through experiments on ImageNet, demonstrating that DLD consistently outperforms prior defenses--even under worst-case adaptive attacks--while preserving the model's predicted labels.

📄 PDF Abstract BibTeX arXiv:2602.08679

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

PlugAT: A Plug and Play Module to Defend against Textual Adversarial Attack

2022-10-01 · COLING 2022 10 · Rui Zheng, Rong Bao, Qin Liu, Tao Gui 외

Adversarial training, which minimizes the loss of adversarially perturbed examples, has received considerable attention. However, these methods require modifying all model parameters and optimizing the model from scratch…

Adversarial AttackDomain Adaptationtext-classificationText Classification

The Linear Geometry of Interpretable Tokens: Jailbreaking Attacks and Defenses for Unlearned Diffusion Models

2025-04-30 · Siyi Chen, Yimeng Zhang, Sijia Liu, Qing Qu arxiv

Diffusion models excel at generating high-quality images but can memorize and reproduce harmful concepts when prompted. Although fine-tuning methods have been proposed to unlearn a target concept, they struggle to fully …

LoRA Patching: Exposing the Fragility of Proactive Defenses against Deepfakes

2025-10-04 · Zuomin Qu, Yimao Guo, Qianyue Hu, Wei Lu arxiv

Deepfakes pose significant societal risks, motivating the development of proactive defenses that embed adversarial perturbations in facial images to prevent manipulation. However, in this paper, we show that these preemp…

KCES: Training-Free Defense for Robust Graph Neural Networks via Kernel Complexity

2025-06-13 · Yaning Jia, Shenyang Deng, Chiyu Ma, Yaoqing Yang 외

Graph Neural Networks (GNNs) have achieved impressive success across a wide range of graph-based tasks, yet they remain highly vulnerable to small, imperceptible perturbations and adversarial attacks. Although numerous d…

Robust Vision-Language Models via Tensor Decomposition: A Defense Against Adversarial Attacks

2025-09-19 · Het Patel, Muzammil Allie, Qian Zhang, Jia Chen 외 arxiv

Vision language models (VLMs) excel in multimodal understanding but are prone to adversarial attacks. Existing defenses often demand costly retraining or significant architecture changes. We introduce a lightweight defen…