Making Tagging Systems Resistant to Tricky Spam Attacks

Tagging systems are known vulnerable to tag spam. While there have been efforts aiming at addressing this problem, tricky spam attackers could exploit and leverage vulnerabilities within them to invalidate these seemingly robust efforts. Rather than fully solving the problem of tricky spam attacks which has been demonstrated almost impossible, this paper aims to mitigate the effect from tricky spam attacks, providing high-quality tag search results to normal users. To achieve this goal, we leverage two key insights exploited from current tagging systems, 1) altruistic users and 2) social networking context, to design a novel reputation-based spam-resistant approach. With our approach, it would be very high probability for normal users to pick their expected content from tag search results, thus decreasing the effect of tag spam. Our experimental results indicate the approach makes at best-effort defense against tricky spam attacks and work better than existing efforts.