Summary of Graded Suspiciousness Of Adversarial Texts to Human, by Shakila Mahjabin Tonni et al.
Graded Suspiciousness of Adversarial Texts to Human
by Shakila Mahjabin Tonni, Pedro Faustini, Mark Dras
First submitted to arxiv on: 6 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computation and Language (cs.CL); Cryptography and Security (cs.CR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper investigates adversarial texts that aim to degrade deep neural network (DNN) performance in the realm of natural language processing. Unlike image-based adversarial examples, which focus on imperceptibility, adversarial texts must maintain semantic similarity and remain undetected by human readers while deceiving NLP systems or bypassing filters. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Adversarial examples are carefully designed inputs that intentionally degrade deep neural network (DNN) performance in both image and text domains. In the context of text-based DNNs, adversarial texts must balance semantic similarity with imperceptibility to human readers while deceiving natural language processing (NLP) systems or bypassing filters. |
Keywords
» Artificial intelligence » Natural language processing » Neural network » Nlp
