# Beyond Deceptive Flatness: Dual-Order Solution for Strengthening Adversarial Transferability

Source: [Beyond Deceptive Flatness: Dual-Order Solution for Strengthening Adversarial Transferability](<https://www.sota2.com/research/paper/690988943ef7ccd74e5e5e75>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-05T05:04:59.190Z

Authors: Zhixuan Zhang, Pingyu Wang, Xingjian Zheng, Linbo Qing, Qi Liu

Published: 2025-11-03T05:26:43.000Z

## Abstract

Transferable attacks generate adversarial examples on surrogate models to fool unknown victim models, posing real-world threats and growing research interest. Despite focusing on flat losses for transferable adversarial examples, recent studies still fall into suboptimal regions, especially the flat-yet-sharp areas, termed as deceptive flatness. In this paper, we introduce a novel black-box gradient-based transferable attack from a perspective of dual-order information. Specifically, we feasibly propose Adversarial Flatness (AF) to the deceptive flatness problem and a theoretical assurance for adversarial transferability. Based on this, using an efficient approximation of our objective, we instantiate our attack as Adversarial Flatness Attack (AFA), addressing the altered gradient sign issue. Additionally, to further improve the attack ability, we devise MonteCarlo Adversarial Sampling (MCAS) by enhancing the inner-loop sampling efficiency. The comprehensive results on ImageNet-compatible dataset demonstrate superiority over six baselines, generating adversarial examples in flatter regions and boosting transferability across model architectures. When tested on input transformation attacks or the Baidu Cloud API, our method outperforms baselines.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.01240>)

[PDF](<https://arxiv.org/pdf/2511.01240.pdf>)
