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 2410.01574cs.CVcs.LG
收藏

AI生成图像检测器在现实世界中的对抗鲁棒性

Adversarial Robustness of AI-Generated Image Detectors in the Real World

CISPA Helmholtz Center for Information Security(CISPA海德堡信息安全中心);Ruhr University Bochum(博尔塔伦大学)

Sina Mavali, Jonas Ricker, David Pape, Asja Fischer, Lea Schönherr

AI总结:

研究现实条件下AI生成图像检测器对对抗样本的脆弱性,通过四种检测方法和五种攻击算法证明攻击者无需内部知识即可显著降低分类性能,并发现攻击在图像上传至社交媒体等降质后仍有效。

摘要:

生成式人工智能(GenAI)能力的快速进步伴随着其被滥用的令人担忧的增长。特别是以图像形式生成可信的错误信息,对公众对民主进程的信任构成重大威胁。因此,迫切需要开发工具来可靠地区分真实内容和AI生成内容。大多数检测方法基于训练用于识别取证伪迹的神经网络。在这项工作中,我们证明了当前最先进的分类器在现实世界条件下容易受到对抗样本的攻击。通过包括四种检测方法和五种攻击算法的大量实验,我们表明攻击者可以在不了解检测器内部架构的情况下显著降低分类性能。值得注意的是,即使图像在上传到社交媒体平台等过程中被降质,大多数攻击仍然有效。在一项案例研究中,我们通过对HIVE(一个专有的在线GenAI媒体检测器)进行黑盒攻击,证明了这些鲁棒性挑战也存在于商业工具中。此外,我们评估了使用鲁棒预训练模型生成的特征的鲁棒性,并表明这增加了鲁棒性,同时在良性输入上未达到性能。这些结果,加上GenAI侵蚀公众信任的潜力日益增加,强调了需要更多研究和新的视角来防止其滥用的方法。

英文摘要:

The rapid advancement of Generative Artificial Intelligence (GenAI) capabilities is accompanied by a concerning rise in its misuse. In particular the generation of credible misinformation in the form of images poses a significant threat to the public trust in democratic processes. Consequently, there is an urgent need to develop tools to reliably distinguish between authentic and AI-generated content. The majority of detection methods are based on neural networks that are trained to recognize forensic artifacts. In this work, we demonstrate that current state-of-the-art classifiers are vulnerable to adversarial examples under real-world conditions. Through extensive experiments, comprising four detection methods and five attack algorithms, we show that an attacker can dramatically decrease classification performance, without internal knowledge of the detector's architecture. Notably, most attacks remain effective even when images are degraded during the upload to, e.g., social media platforms. In a case study, we demonstrate that these robustness challenges are also found in commercial tools by conducting black-box attacks on HIVE, a proprietary online GenAI media detector. In addition, we evaluate the robustness of using generated features of a robust pre-trained model and showed that this increases the robustness, while not reaching the performance on benign inputs. These results, along with the increasing potential of GenAI to erode public trust, underscore the need for more research and new perspectives on methods to prevent its misuse.

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。

↑