Summary of Llm App Squatting and Cloning, by Yinglin Xie et al.
LLM App Squatting and Cloning
by Yinglin Xie, Xinyi Hou, Yanjie Zhao, Kai Chen, Haoyu Wang
First submitted to arxiv on: 12 Nov 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: 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 study investigates impersonation tactics in Large Language Model (LLM) stores, where malicious actors exploit popular app names to deceive users. The authors develop a custom-built tool, LLMappCrazy, which integrates Levenshtein distance and BERT-based semantic analysis to detect squatting and cloning. Using this tool, the study finds over 5,000 squatting apps and 9,575 cloning cases across six major platforms, with 18.7% of squatting apps and 4.9% of cloning apps exhibiting malicious behavior. The paper’s findings demonstrate the need for LLM app store integrity solutions to prevent impersonation attacks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study looks at a problem in online stores where people pretend to be popular apps or websites to trick users. Researchers created a special tool to find these fake apps and found over 5,000 of them on popular platforms! They also found that some of these fake apps spread malware or showed fake news. This is an important issue because it can make it hard for people to trust online stores. The study shows how big the problem is and why we need better ways to keep LLM app stores safe. |
Keywords
» Artificial intelligence » Bert » Large language model
