Vera Verto：多模态劫持攻击
Vera Verto: Multimodal Hijacking Attack
AI总结：
本文提出多模态模型劫持攻击 Blender，可将 NLP 任务植入图像分类模型，并在多个数据集上实现最高 95% 的攻击成功率。
摘要：
训练机器学习（ML）模型的成本不断上升，导致训练流程中出现了新的参与方，例如贡献训练数据的用户和提供计算资源的公司。这些新参与方介入 ML 训练过程，为攻击者带来了可利用的新攻击面。该领域近期的一种攻击是模型劫持攻击，攻击者借此劫持受害模型，以实现其自身的（可能是恶意的）劫持任务。然而，模型劫持攻击的范围迄今仅限于同模态任务。本文将模型劫持攻击转化为更一般的多模态场景，其中劫持任务和原始任务在不同模态的数据上执行。具体而言，我们关注攻击者将自然语言处理（NLP）劫持任务植入图像分类模型的场景。为实施该攻击，我们提出了一种新颖的基于编码器-解码器的框架，名为 Blender，它依赖先进的图像和语言模型。实验结果表明，我们的模态劫持攻击在不同设置下均取得了强劲性能。例如，在使用 Sogou news 数据集劫持 STL10、CIFAR-10 和 MNIST 分类器时，我们的攻击分别达到 94%、94% 和 95% 的攻击成功率。
英文摘要：
The increasing cost of training machine learning (ML) models has led to the inclusion of new parties to the training pipeline, such as users who contribute training data and companies that provide computing resources. This involvement of such new parties in the ML training process has introduced new attack surfaces for an adversary to exploit. A recent attack in this domain is the model hijacking attack, whereby an adversary hijacks a victim model to implement their own -- possibly malicious -- hijacking tasks. However, the scope of the model hijacking attack is so far limited to the homogeneous-modality tasks. In this paper, we transform the model hijacking attack into a more general multimodal setting, where the hijacking and original tasks are performed on data of different modalities. Specifically, we focus on the setting where an adversary implements a natural language processing (NLP) hijacking task into an image classification model. To mount the attack, we propose a novel encoder-decoder based framework, namely the Blender, which relies on advanced image and language models. Experimental results show that our modal hijacking attack achieves strong performances in different settings. For instance, our attack achieves 94%, 94%, and 95% attack success rate when using the Sogou news dataset to hijack STL10, CIFAR-10, and MNIST classifiers.
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。
