基于潜在优化与可迁移性增强的隐蔽对抗样本生成统一框架
A Unified Framework for Stealthy Adversarial Generation via Latent Optimization and Transferability Enhancement
AI总结：
针对扩散模型对抗样本生成难以泛化及传统可迁移性策略难以适配的问题，提出一个统一框架，通过图像编辑将传统可迁移性增强策略无缝融入扩散模型对抗样本生成，并在ACM MM25竞赛中获第一名。
摘要：
由于具有强大的图像生成能力，通过图像编辑生成扩散模型对抗样本的方法正迅速流行。然而，由于依赖扩散模型的判别能力，这些基于扩散模型的方法往往难以泛化到传统图像分类任务之外，例如Deepfake检测。此外，用于增强对抗样本可迁移性的传统策略也难以适应这些方法。为了应对这些挑战，我们提出了一个统一框架，通过图像编辑将传统可迁移性增强策略无缝融入基于扩散模型的对抗样本生成中，使其能够应用于更广泛的下游任务。我们的方法在ACM MM25举办的“1st Adversarial Attacks on Deepfake Detectors: A Challenge in the Era of AI-Generated Media”竞赛中获得第一名，验证了该方法的有效性。
英文摘要：
Due to their powerful image generation capabilities, diffusion-based adversarial example generation methods through image editing are rapidly gaining popularity. However, due to reliance on the discriminative capability of the diffusion model, these diffusion-based methods often struggle to generalize beyond conventional image classification tasks, such as in Deepfake detection. Moreover, traditional strategies for enhancing adversarial example transferability are challenging to adapt to these methods. To address these challenges, we propose a unified framework that seamlessly incorporates traditional transferability enhancement strategies into diffusion model-based adversarial example generation via image editing, enabling their application across a wider range of downstream tasks. Our method won first place in the "1st Adversarial Attacks on Deepfake Detectors: A Challenge in the Era of AI-Generated Media" competition at ACM MM25, which validates the effectiveness of our approach.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
