生成标签内聚性和格式良好的对抗性声明
Generating Label Cohesive and Well-Formed Adversarial Claims
摘要：
对抗攻击揭示了训练模型的重要弱点和缺陷。一种有效的攻击类型是通用对抗触发器，它是单独的n-gram，当附加到受攻击的类的实例时，可以欺骗模型预测目标类。然而，对于诸如事实检查之类的推理任务，这些触发器经常会无意中颠倒它们所插入的实例的含义。此外，这种攻击会产生语义上无意义的输入，因为它们只是将触发器连接到现有样本。在这里，我们研究如何生成针对事实检查系统的对抗攻击，这些事实检查系统保留了地面真值含义并且在语义上是有效的。我们扩展了HotFlip攻击算法用于通用触发器生成，通过联合最小化目标类损失的事实检查模型和蕴涵类损失的辅助自然语言推理模型。然后，我们训练一个条件语言模型来生成语义上有效的语句，其中包括找到的通用触发器。我们发现，所产生的攻击保持的方向性和语义有效性的索赔比以前的工作。
英文摘要：
Adversarial attacks reveal important vulnerabilities and flaws of trained models. One potent type of attack are universal adversarial triggers, which are individual n-grams that, when appended to instances of a class under attack, can trick a model into predicting a target class. However, for inference tasks such as fact checking, these triggers often inadvertently invert the meaning of instances they are inserted in. In addition, such attacks produce semantically nonsensical inputs, as they simply concatenate triggers to existing samples. Here, we investigate how to generate adversarial attacks against fact checking systems that preserve the ground truth meaning and are semantically valid. We extend the HotFlip attack algorithm used for universal trigger generation by jointly minimising the target class loss of a fact checking model and the entailment class loss of an auxiliary natural language inference model. We then train a conditional language model to generate semantically valid statements, which include the found universal triggers. We find that the generated attacks maintain the directionality and semantic validity of the claim better than previous work.
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。
