Captcha Attack:让验证码反人类
Captcha Attack: Turning Captchas Against Humanity
摘要:
如今,人们在在线平台上生成和共享大量内容(例如,社交网络、博客)。2021年,19亿日活跃Facebook用户每分钟发布约15万张照片。内容版主不断地监视这些在线平台以防止不适当内容的传播(例如,仇恨言论,裸体图片)。基于深度学习(DL)的进步,自动内容审核员(ACM)可以帮助人类审核员处理大量数据。尽管它们具有优势,但攻击者可以利用DL组件的弱点(例如,预处理,模型)以影响其性能。因此,攻击者可以利用这些技术通过规避ACM来传播不适当的内容。在这项工作中,我们提出了CAPtcha攻击(CAPA),一种对抗性技术,允许用户通过逃避ACM控制在网上传播不适当的文本。CAPA通过生成自定义文本CAPTCHA,利用ACM的粗心设计实现和内部程序漏洞。我们在现实世界的ACM上测试了我们的攻击,结果证实了我们简单而有效的攻击的凶猛性,在大多数情况下达到了100%的规避成功率。同时,我们展示了设计CAPA缓解措施的困难,为CAPTCHA研究领域带来了新的挑战。
英文摘要:
Nowadays, people generate and share massive content on online platforms (e.g., social networks, blogs). In 2021, the 1.9 billion daily active Facebook users posted around 150 thousand photos every minute. Content moderators constantly monitor these online platforms to prevent the spreading of inappropriate content (e.g., hate speech, nudity images). Based on deep learning (DL) advances, Automatic Content Moderators (ACM) help human moderators handle high data volume. Despite their advantages, attackers can exploit weaknesses of DL components (e.g., preprocessing, model) to affect their performance. Therefore, an attacker can leverage such techniques to spread inappropriate content by evading ACM. In this work, we propose CAPtcha Attack (CAPA), an adversarial technique that allows users to spread inappropriate text online by evading ACM controls. CAPA, by generating custom textual CAPTCHAs, exploits ACM's careless design implementations and internal procedures vulnerabilities. We test our attack on real-world ACM, and the results confirm the ferocity of our simple yet effective attack, reaching up to a 100% evasion success in most cases. At the same time, we demonstrate the difficulties in designing CAPA mitigations, opening new challenges in CAPTCHAs research area.
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。