arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.03444cs.CRcs.AI
收藏

迈向深度网络隐写术:从网络到网络

Towards Deep Network Steganography: From Networks to Networks

Fudan University(复旦大学)

Guobiao Li, Sheng Li, Meiling Li, Zhenxing Qian, Xinpeng Zhang

AI总结:

本文提出深度网络隐写术,通过基于梯度的滤波器插入、密钥边信息隐藏和部分优化策略,将秘密DNN模型伪装成执行普通任务的隐写DNN模型,实现DNN模型的隐蔽传输。

摘要:

随着深度神经网络(DNN)的广泛应用,如何在公共信道中隐蔽地传输DNN模型引起了我们的关注,尤其是那些为秘密学习任务训练的模型。本文提出了用于DNN模型隐蔽通信的深度网络隐写术。与现有隐写方案侧重于对载体数据进行细微修改以容纳秘密不同,我们的方案以学习任务为导向,其中秘密DNN模型的学习任务(称为秘密学习任务)被伪装成在隐写DNN模型中执行的另一个普通学习任务(称为隐写学习任务)。为此,我们提出了一种基于梯度的滤波器插入方案,将干扰滤波器插入秘密DNN模型中的重要位置,以形成隐写DNN模型。然后,利用密钥通过边信息隐藏将这些位置嵌入到隐写DNN模型中。最后,我们通过部分优化策略激活干扰滤波器,使生成的隐写DNN模型能够执行隐写学习任务。我们在任务内隐写和任务间隐写(即秘密学习任务与隐写学习任务分别属于相同和不同类别)上进行了实验,两者均证明了我们所提方法在DNN模型隐蔽通信中的有效性。

英文摘要:

With the widespread applications of the deep neural network (DNN), how to covertly transmit the DNN models in public channels brings us the attention, especially for those trained for secret-learning tasks. In this paper, we propose deep network steganography for the covert communication of DNN models. Unlike the existing steganography schemes which focus on the subtle modification of the cover data to accommodate the secrets, our scheme is learning task oriented, where the learning task of the secret DNN model (termed as secret-learning task) is disguised into another ordinary learning task conducted in a stego DNN model (termed as stego-learning task). To this end, we propose a gradient-based filter insertion scheme to insert interference filters into the important positions in the secret DNN model to form a stego DNN model. These positions are then embedded into the stego DNN model using a key by side information hiding. Finally, we activate the interference filters by a partial optimization strategy, such that the generated stego DNN model works on the stego-learning task. We conduct the experiments on both the intra-task steganography and inter-task steganography (i.e., the secret and stego-learning tasks belong to the same and different categories), both of which demonstrate the effectiveness of our proposed method for covert communication of DNN models.

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。

↑