生成自然语义的对抗触发词，让模型误判情感分析结果。
Universal Adversarial Triggers
- 用词性过滤和困惑度损失生成语法自然的触发词
- 在SST数据集上使分类准确率降至0.04至0.12
- 可用于训练鲁棒模型，提升防御能力
近期研究显示，现代NLP模型在情感分析到语言生成等多种任务中均易受通用对抗攻击影响，此类攻击使用通用触发序列干扰模型。尽管攻击有效，但现有触发词语法混乱、不自然。本文提出结合词性过滤与困惑度损失的新方法，生成更接近自然语言的触发词。在SST数据集的情感分析任务中，该方法生成的触发词可使正负情感预测准确率分别降至0.04和0.12。通过使用生成的触发词进行对抗训练，模型准确率从0.12提升至0.48。研究旨在展示自然触发词可增强攻击隐蔽性，并推动鲁棒模型的发展。
原文摘要 · Abstract (English)
Recent works have illustrated that modern NLP models trained for diverse tasks ranging from sentiment analysis to language generation succumb to universal adversarial attacks, a class of input-agnostic attacks where a common trigger sequence is used to attack the model. Although these attacks are successful, the triggers generated by such attacks are ungrammatical and unnatural. Our work proposes a novel technique combining parts-of-speech filtering and perplexity based loss function to generate sensible triggers that are closer to natural phrases. For the task of sentiment analysis on the SST dataset, the method produces sensible triggers that achieve accuracies as low as 0.04 and 0.12 for flipping positive to negative predictions and vice-versa. To build robust models, we also perform adversarial training using the generated triggers that increases the accuracy of the model from 0.12 to 0.48. We aim to illustrate that adversarial attacks can be made difficult to detect by generating sensible triggers, and to facilitate robust model development through relevant defenses.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。