paper-with-me

홈 › Papers

RNN-Guard: Certified Robustness Against Multi-frame Attacks for Recurrent Neural Networks

2023-04-17 · Yunruo Zhang, Tianyu Du, Shouling Ji, Peng Tang, Shanqing Guo

It is well-known that recurrent neural networks (RNNs), although widely used, are vulnerable to adversarial attacks including one-frame attacks and multi-frame attacks. Though a few certified defenses exist to provide guaranteed robustness against one-frame attacks, we prove that defending against multi-frame attacks remains a challenging problem due to their enormous perturbation space. In this paper, we propose the first certified defense against multi-frame attacks for RNNs called RNN-Guard. To address the above challenge, we adopt the perturb-all-frame strategy to construct perturbation spaces consistent with those in multi-frame attacks. However, the perturb-all-frame strategy causes a precision issue in linear relaxations. To address this issue, we introduce a novel abstract domain called InterZono and design tighter relaxations. We prove that InterZono is more precise than Zonotope yet carries the same time complexity. Experimental evaluations across various datasets and model structures show that the certified robust accuracy calculated by RNN-Guard with InterZono is up to 2.18 times higher than that with Zonotope. In addition, we extend RNN-Guard as the first certified training method against multi-frame attacks to directly enhance RNNs' robustness. The results show that the certified robust accuracy of models trained with RNN-Guard against multi-frame attacks is 15.47 to 67.65 percentage points higher than those with other training methods.

📄 PDF Abstract BibTeX arXiv:2304.07980

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

CeTAD: Towards Certified Toxicity-Aware Distance in Vision Language Models

2025-03-08 · Xiangyu Yin, Jiaxu Liu, Zhen Chen, Jinwei Hu 외

Recent advances in large vision-language models (VLMs) have demonstrated remarkable success across a wide range of visual understanding tasks. However, the robustness of these models against jailbreak attacks remains an …

Towards Universal Certified Robustness with Multi-Norm Training

2024-10-03 · Enyi Jiang, David S. Cheung, Gagandeep Singh

Existing certified training methods can only train models to be robust against a certain perturbation type (e.g. $l_\infty$ or $l_2$). However, an $l_\infty$ certifiably robust model may not be certifiably robust against…

Scalable and Precise Patch Robustness Certification for Deep Learning Models with Top-k Predictions

2025-07-31 · Qilin Zhou, Haipeng Wang, Zhengyuan Wei, W. K. Chan arxiv

Patch robustness certification is an emerging verification approach for defending against adversarial patch attacks with provable guarantees for deep learning systems. Certified recovery techniques guarantee the predicti…

UniCR: Universally Approximated Certified Robustness via Randomized Smoothing

2022-07-05 · Hanbin Hong, Binghui Wang, Yuan Hong

We study certified robustness of machine learning classifiers against adversarial perturbations. In particular, we propose the first universally approximated certified robustness (UniCR) framework, which can approximate …

PointGuard: Provably Robust 3D Point Cloud Classification

2021-03-04 · CVPR 2021 1 · Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong

3D point cloud classification has many safety-critical applications such as autonomous driving and robotic grasping. However, several studies showed that it is vulnerable to adversarial attacks. In particular, an attacke…

3D Point Cloud ClassificationAutonomous DrivingClassificationGeneral Classification+2