Spear Phishing is a type of cyber-attack where the attacker sends hyperlinks through email on well-researched targets. The objective is to obtain sensitive information by imitating oneself as a trustworthy website. In recent times, deep learning has become the standard for defending against such attacks. However, these architectures were designed with only defense in mind. Moreover, the attacker's perspective and motivation are absent while creating such models. To address this, we need a game-theoretic approach to understand the perspective of the attacker (Hacker) and the defender (Phishing URL detector). We propose a Conditional Generative Adversarial Network with novel training strategy for real-time phishing URL detection. Additionally, we train our architecture in a semi-supervised manner to distinguish between adversarial and real examples, along with detecting malicious and benign URLs. We also design two games between the attacker and defender in training and deployment settings by utilizing the game-theoretic perspective. Our experiments confirm that the proposed architecture surpasses recent state-of-the-art architectures for phishing URLs detection.

翻译：Spear Phishing是一种网络攻击,攻击者通过电子邮件在经过充分研究的目标上发送超文本链接。 目标是通过模仿自己成为一个值得信赖的网站来获取敏感信息。 近些年来, 深层次的学习已成为防范这类攻击的标准。 然而, 这些建筑的设计仅仅以防御为目的。 此外, 在创建这些模型时, 攻击者的观点和动机是不存在的。 为了解决这个问题, 我们需要一种游戏理论方法来理解攻击者( 黑克) 和防御者( 光学 URL 探测器) 的观点。 我们建议建立一个具有新型的实时网络, 培训战略来实时进行网络光学的检测。 此外, 我们用半超超能力的方式培训我们的架构, 以区分对抗性和真实的范例, 同时检测恶意和无害的 URL 。 我们还设计了两个游戏, 攻击者与攻击者在培训和部署环境中的防御者之间, 利用游戏- 理论角度进行训练 。 我们的实验证实, 提议的架构超过了最新的网络探测的最新状态结构 。