Summary of Sscae — Semantic, Syntactic, and Context-aware Natural Language Adversarial Examples Generator, by Javad Rafiei Asl et al.
SSCAE – Semantic, Syntactic, and Context-aware natural language Adversarial Examples generator
by Javad Rafiei Asl, Mohammad H. Rafiei, Manar Alohaly, Daniel Takabi
First submitted to arxiv on: 18 Mar 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
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 The paper proposes a novel adversarial attack model called SSCAE (Semantic, Syntactic, and Context-aware) to generate high-quality Adversarial Examples (AEs) for natural language processing. The authors introduce a practical and efficient method that identifies important words using masked language models and evaluates initial sets of substitutions based on semantic and syntactic characteristics. The proposed approach uses a dynamic threshold to capture more efficient perturbations and a local greedy search to generate high-quality AEs that preserve semantic consistency and syntactical requirements. Experimental results demonstrate the superiority of SSCAE over existing models in terms of semantic consistency, query number, and perturbation rate. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper introduces a new way to make language models stronger against attacks. It’s like training a superhero model to fight against bad guys trying to trick it. The authors created a tool called SSCAE that can generate good fake text that is hard for the model to detect. They tested it on many different scenarios and showed that it works better than other methods. |
Keywords
* Artificial intelligence * Natural language processing
