paper-with-me

Papers

Transferable Adversarial Perturbations

2018-09-01 · ECCV 2018 9 · Wen Zhou, Xin Hou, Yongjun Chen, Mengyun Tang, Xiangqi Huang, Xiang Gan, Yong Yang

State-of-the-art deep neural network classifiers are highly vulnerable to adversarial examples which are designed to mislead classifiers with a very small perturbation. However, the performance of black-box attacks (without knowledge of the model parameters) against deployed models always degrades significantly. In this paper, We propose a novel way of perturbations for adversarial examples to enable black-box transfer. We first show that maximizing distance between natural images and their adversarial examples in the intermediate feature maps can improve both white-box attacks (with knowledge of the model parameters) and black-box attacks. We also show that smooth regularization on adversarial perturbations enables transferring across models. Extensive experimental results show that our approach outperforms state-of-the-art methods both in white-box and black-box attacks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MAPE: Defending Against Transferable Adversarial Attacks Using Multi-Source Adversarial Perturbations Elimination

2026-06-30 · Xinlei Liu, Jichao Xie, Tao Hu, Peng Yi 외 arxiv

Neural networks are vulnerable to meticulously crafted adversarial examples, leading to high-confidence misclassifications in image classification tasks. Due to their consistency with regular input patterns and the absen…

Image Classification

Diverse Generative Perturbations on Attention Space for Transferable Adversarial Attacks

2022-08-11 · Woo Jae Kim, Seunghoon Hong, Sung-Eui Yoon

Adversarial attacks with improved transferability - the ability of an adversarial example crafted on a known model to also fool unknown models - have recently received much attention due to their practicality. Neverthele…

Diversity

Learning to Learn Transferable Attack

2021-12-10 · Shuman Fang, Jie Li, Xianming Lin, Rongrong Ji

Transfer adversarial attack is a non-trivial black-box adversarial attack that aims to craft adversarial perturbations on the surrogate model and then apply such perturbations to the victim model. However, the transferab…

Adversarial AttackData AugmentationMeta-Learning

Rethinking Transferable Adversarial Attacks on Point Clouds from a Compact Subspace Perspective

2026-01-30 · Keke Tang, Xianheng Liu, Weilong Peng, Xiaofei Wang 외 arxiv

Transferable adversarial attacks on point clouds remain challenging, as existing methods often rely on model-specific gradients or heuristics that limit generalization to unseen architectures. In this paper, we rethink a…

Point Clouds

Improving Adversarial Transferability via Model Alignment

2023-11-30 · Avery Ma, Amir-Massoud Farahmand, Yangchen Pan, Philip Torr 외

Neural networks are susceptible to adversarial perturbations that are transferable across different models. In this paper, we introduce a novel model alignment technique aimed at improving a given source model's ability …

model