Safeguarding data from unauthorized exploitation is vital for privacy and security, especially in recent rampant research in security breach such as adversarial/membership attacks. To this end, \textit{unlearnable examples} (UEs) have been recently proposed as a compelling protection, by adding imperceptible perturbation to data so that models trained on them cannot classify them accurately on original clean distribution. Unfortunately, we find UEs provide a false sense of security, because they cannot stop unauthorized users from utilizing other unprotected data to remove the protection, by turning unlearnable data into learnable again. Motivated by this observation, we formally define a new threat by introducing \textit{learnable unauthorized examples} (LEs) which are UEs with their protection removed. The core of this approach is a novel purification process that projects UEs onto the manifold of LEs. This is realized by a new joint-conditional diffusion model which denoises UEs conditioned on the pixel and perceptual similarity between UEs and LEs. Extensive experiments demonstrate that LE delivers state-of-the-art countering performance against both supervised UEs and unsupervised UEs in various scenarios, which is the first generalizable countermeasure to UEs across supervised learning and unsupervised learning. Our code is available at \url{https://github.com/jiangw-0/LE_JCDP}.

翻译：保护数据免遭未经授权的利用对隐私和安全至关重要，尤其是在近期针对安全漏洞（如对抗性攻击/成员推理攻击）的研究泛滥的背景下。为此，最新提出的“不可学习示例”（UEs）通过向数据添加难以察觉的扰动，使得在其上训练的模型无法准确分类原始干净分布中的数据，从而成为一种具有说服力的保护措施。然而，我们发现UEs提供了一种虚假的安全感，因为它们无法阻止未经授权的用户利用其他未受保护的数据来移除这种保护，从而使不可学习的数据重新变得可学习。受此观察启发，我们正式定义了一种新型威胁，即“可学习未经授权示例”（LEs），这些示例是移除了保护的UEs。该方法的核心是一种新颖的净化过程，将UEs投影到LEs的流形上。这通过一种全新的联合条件扩散模型实现，该模型在像素级别和感知相似性上基于UEs与LEs的相似性对UEs进行去噪。大量实验表明，LE在各种场景下对监督式UEs和无监督式UEs均能达到最先进的对抗性能，这是首个在监督学习和无监督学习领域均具备泛化能力的UEs对抗策略。我们的代码开源在：\url{https://github.com/jiangw-0/LE_JCDP}。