paper-with-me

Papers

Exploring and Enhancing the Transferability of Adversarial Examples

2019-05-01 · ICLR 2019 5 · Lei Wu, Zhanxing Zhu, Cheng Tai

State-of-the-art deep neural networks are vulnerable to adversarial examples, formed by applying small but malicious perturbations to the original inputs. Moreover, the perturbations can \textit{transfer across models}: adversarial examples generated for a specific model will often mislead other unseen models. Consequently the adversary can leverage it to attack deployed systems without any query, which severely hinders the application of deep learning, especially in the safety-critical areas. In this work, we empirically study how two classes of factors those might influence the transferability of adversarial examples. One is about model-specific factors, including network architecture, model capacity and test accuracy. The other is the local smoothness of loss surface for constructing adversarial examples. Inspired by these understandings on the transferability of adversarial examples, we then propose a simple but effective strategy to enhance the transferability, whose effectiveness is confirmed by a variety of experiments on both CIFAR-10 and ImageNet datasets.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness

2023-11-10 · Mingyuan Fan, Xiaodan Li, Cen Chen, Wenmeng Zhou 외

A prevailing belief in attack and defense community is that the higher flatness of adversarial examples enables their better cross-model transferability, leading to a growing interest in employing sharpness-aware minimiz…

Adversarial AttackDiversity

Boosting Adversarial Transferability via Commonality-Oriented Gradient Optimization

2025-06-08 · Yanting Gao, Yepeng Liu, Junming Liu, Qi Zhang 외

Exploring effective and transferable adversarial examples is vital for understanding the characteristics and mechanisms of Vision Transformers (ViTs). However, adversarial examples generated from surrogate models often e…

Exploring Frequencies via Feature Mixing and Meta-Learning for Improving Adversarial Transferability

2024-05-06 · Juanjuan Weng, Zhiming Luo, Shaozi Li

Recent studies have shown that Deep Neural Networks (DNNs) are susceptible to adversarial attacks, with frequency-domain analysis underscoring the significance of high-frequency components in influencing model prediction…

Meta-Learning

Boosting the Adversarial Transferability of Surrogate Models with Dark Knowledge

2022-06-16 · Dingcheng Yang, Zihao Xiao, Wenjian Yu

Deep neural networks (DNNs) are vulnerable to adversarial examples. And, the adversarial examples have transferability, which means that an adversarial example for a DNN model can fool another model with a non-trivial pr…

Adversarial AttackFace VerificationImage Classification

Boosting the Targeted Transferability of Adversarial Examples via Salient Region & Weighted Feature Drop

2024-11-11 · Shanjun Xu, Linghui Li, Kaiguo Yuan, Bingyu Li

Deep neural networks can be vulnerable to adversarially crafted examples, presenting significant risks to practical applications. A prevalent approach for adversarial attacks relies on the transferability of adversarial …