arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.01969cs.CR
收藏

AI模型LSB攻击的隐写分析

Steganalysis of AI Models LSB Attacks

Daniel Gilkarov, Ran Dubin

AI总结:

针对共享AI模型中的恶意LSB隐写威胁,论文提出3种有监督与无监督隐写分析方法并开源,发现检测效果取决于攻击位位置。

摘要:

人工智能在过去十年中取得了重大进展,推动模型共享日益普及。model zoo生态系统作为预训练AI模型的仓库,促进了AI开源社区的发展,也开辟了网络风险的新途径。恶意攻击者可以利用共享模型发起网络攻击。本工作聚焦于注入AI模型中的恶意最低有效位(LSB)隐写术的隐写分析,也是首个聚焦AI模型攻击的工作。针对这一威胁,本文提出一种专门定制的隐写分析方法,基于有监督和无监督AI检测隐写分析方法,检测并缓解恶意LSB隐写攻击。我们提出的技术旨在维护共享模型的完整性、保护用户信任,并保持AI社区开放协作的势头。在本工作中,我们提出3种隐写分析方法并开源代码。我们发现,隐写分析的成功取决于LSB攻击位置。如果攻击者决定利用LSB中的最低有效位,检测攻击的能力较低;然而,如果攻击位于最重要的LSB位,几乎可以以完美准确率检测到攻击。

英文摘要:

Artificial intelligence has made significant progress in the last decade, leading to a rise in the popularity of model sharing. The model zoo ecosystem, a repository of pre-trained AI models, has advanced the AI open-source community and opened new avenues for cyber risks. Malicious attackers can exploit shared models to launch cyber-attacks. This work focuses on the steganalysis of injected malicious Least Significant Bit (LSB) steganography into AI models, and it is the first work focusing on AI model attacks. In response to this threat, this paper presents a steganalysis method specifically tailored to detect and mitigate malicious LSB steganography attacks based on supervised and unsupervised AI detection steganalysis methods. Our proposed technique aims to preserve the integrity of shared models, protect user trust, and maintain the momentum of open collaboration within the AI community. In this work, we propose 3 steganalysis methods and open source our code. We found that the success of the steganalysis depends on the LSB attack location. If the attacker decides to exploit the least significant bits in the LSB, the ability to detect the attacks is low. However, if the attack is in the most significant LSB bits, the attack can be detected with almost perfect accuracy.

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。

↑