论文标题
测量错误的安全感
Measuring the False Sense of Security
论文作者
论文摘要
最近，几篇论文证明了拟议的对抗防御能力之一。依靠这种现象的防御措施被认为是失败的，很容易被打破。尽管如此，几乎没有研究衡量梯度掩盖现象并在不同网络中对其程度进行比较的现象。在这项工作中，我们调查了其在其子弹的镜头下梯度掩盖的，与它是一种二进制现象的想法背离了。我们建议并激励几个指标，对涉嫌表现出不同程度的梯度掩盖的防御措施进行广泛的经验测试。这些在计算上比强烈的攻击便宜，可以在模型之间进行比较，并且不需要对特定模型进行量身定制攻击的大量时间投资。我们的结果表明，指标成功地衡量了不同网络跨越梯度掩盖的程度
Recently, several papers have demonstrated how widespread gradient masking is amongst proposed adversarial defenses. Defenses that rely on this phenomenon are considered failed, and can easily be broken. Despite this, there has been little investigation into ways of measuring the phenomenon of gradient masking and enabling comparisons of its extent amongst different networks. In this work, we investigate gradient masking under the lens of its mensurability, departing from the idea that it is a binary phenomenon. We propose and motivate several metrics for it, performing extensive empirical tests on defenses suspected of exhibiting different degrees of gradient masking. These are computationally cheaper than strong attacks, enable comparisons between models, and do not require the large time investment of tailor-made attacks for specific models. Our results reveal metrics that are successful in measuring the extent of gradient masking across different networks
