Summary of Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models, by Alkis Kalavasis et al.
Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models
by Alkis Kalavasis, Amin Karbasi, Argyris Oikonomou, Katerina Sotiraki, Grigoris Velegkas, Manolis Zampetakis
First submitted to arxiv on: 9 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); Machine Learning (stat.ML)
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 examines the threat of undetectable backdoors in machine learning (ML) models developed by external expert firms for high-stakes domains like finance and healthcare. These backdoors, introduced by Goldwasser et al. (FOCS ’22), enable the model designer to manipulate the input data, altering the model’s outcome. The investigation focuses on identifying these insidious attacks, which can be undetected despite their potential to significantly impact critical decision-making processes. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper looks at a problem where artificial intelligence models used in important fields like banking and healthcare can be tricked into making wrong decisions by someone who built the model. This is called an “undetectable backdoor.” The researchers are trying to figure out how to spot these hidden tricks, which could have big consequences. |
Keywords
» Artificial intelligence » Machine learning
