arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.09684cs.CRcs.AI
收藏

用于模型完整性验证的基于决策的迭代脆弱水印

Decision-based iterative fragile watermarking for model integrity verification

East China Normal University(华东师范大学);Anhui University(安徽大学);Tsinghua University(清华大学);Fudan University(复旦大学)

Zhaoxia Yin, Heng Yin, Hang Su, Xinpeng Zhang, Zhenzhe Gao

AI总结:

提出一种基于决策的迭代脆弱水印算法,通过将正常样本转换为对模型参数变化高度敏感的脆弱样本来验证云托管基础模型的完整性,该方法在黑盒环境下运行且不依赖特定结构,在检测精度与视觉质量上优于现有技术。

摘要:

通常,基础模型托管在云服务器上以满足对其服务的高需求。然而,这使其面临安全风险,因为攻击者可以在将其上传到云端或从本地系统传输后对其进行修改。为了解决这个问题,我们提出了一种基于决策的迭代脆弱水印算法,该算法将正常训练样本转换为对模型变化敏感的脆弱样本。然后,在验证期间,我们比较原始模型和受损模型中敏感样本的输出,以评估模型的完整性。所提出的脆弱水印算法是一个优化问题,旨在最小化目标模型在输入转换样本时输出的预测概率分布的方差。我们通过多次迭代将正常样本转换为脆弱样本。我们的方法具有以下优势:(1)样本的迭代更新以基于决策的黑盒方式进行,仅依赖于目标模型的预测概率分布,这降低了暴露于对抗性攻击的风险;(2)小幅多次迭代的方法使脆弱样本在视觉上表现良好,在 TinyImageNet 中与原始样本相比 PSNR 达到 55 dB;(3)即使模型整体参数发生 1e-4 量级的变化,脆弱样本也能检测到此类变化;(4)该方法不依赖于特定的模型结构和数据集。我们在多个模型和数据集上证明了我们方法的有效性,并表明它优于当前最先进的技术。

英文摘要:

Typically, foundation models are hosted on cloud servers to meet the high demand for their services. However, this exposes them to security risks, as attackers can modify them after uploading to the cloud or transferring from a local system. To address this issue, we propose an iterative decision-based fragile watermarking algorithm that transforms normal training samples into fragile samples that are sensitive to model changes. We then compare the output of sensitive samples from the original model to that of the compromised model during validation to assess the model's completeness.The proposed fragile watermarking algorithm is an optimization problem that aims to minimize the variance of the predicted probability distribution outputed by the target model when fed with the converted sample.We convert normal samples to fragile samples through multiple iterations. Our method has some advantages: (1) the iterative update of samples is done in a decision-based black-box manner, relying solely on the predicted probability distribution of the target model, which reduces the risk of exposure to adversarial attacks, (2) the small-amplitude multiple iterations approach allows the fragile samples to perform well visually, with a PSNR of 55 dB in TinyImageNet compared to the original samples, (3) even with changes in the overall parameters of the model of magnitude 1e-4, the fragile samples can detect such changes, and (4) the method is independent of the specific model structure and dataset. We demonstrate the effectiveness of our method on multiple models and datasets, and show that it outperforms the current state-of-the-art.

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。

↑