arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2011.04743cs.CLcs.CR
收藏

对抗性语义冲突

Adversarial Semantic Collisions

Cornell University(康奈尔大学);Cornell Tech(康奈尔科技校区)

Congzheng Song, Alexander M. Rush, Vitaly Shmatikov

摘要:

我们研究语义冲突:语义上不相关但被NLP模型判断为相似的文本。我们开发了基于梯度的方法来生成语义冲突,并证明了许多任务的最先进的模型,这些任务依赖于分析文本的含义和相似性-包括释义识别,文档检索,响应建议和提取摘要-容易受到语义冲突的影响。例如,给定一个目标查询,将特制的冲突插入到不相关的文档中可以将其检索排名从1000移到前3。我们将展示如何生成语义冲突,逃避基于困惑的过滤,并讨论其他潜在的缓解。我们的代码可在https://github.com/csong27/collision-bert上获得。

英文摘要:

We study semantic collisions: texts that are semantically unrelated but judged as similar by NLP models. We develop gradient-based approaches for generating semantic collisions and demonstrate that state-of-the-art models for many tasks which rely on analyzing the meaning and similarity of texts-- including paraphrase identification, document retrieval, response suggestion, and extractive summarization-- are vulnerable to semantic collisions. For example, given a target query, inserting a crafted collision into an irrelevant document can shift its retrieval rank from 1000 to top 3. We show how to generate semantic collisions that evade perplexity-based filtering and discuss other potential mitigations. Our code is available at https://github.com/csong27/collision-bert.

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。

↑