Summary of Backdoor Attack Against One-class Sequential Anomaly Detection Models, by He Cheng and Shuhan Yuan
Backdoor Attack against One-Class Sequential Anomaly Detection Models
by He Cheng, Shuhan Yuan
First submitted to arxiv on: 15 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Information Theory (cs.IT)
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 proposes a novel backdoor attack strategy that compromises deep sequential anomaly detection models, highlighting a critical security threat in this field. Specifically, the approach involves generating imperceptible triggers by perturbing benign normal data and injecting these triggers into the model to manipulate its decisions. The results demonstrate the effectiveness of this strategy on two well-established one-class anomaly detection models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about finding ways to trick machines that detect unusual patterns in data. These machines are important for things like detecting strange medical test results or unusual bank transactions. But, right now, these machines can be easily tricked into thinking normal things are weird. The researchers came up with a new way to trick these machines by adding tiny changes to the data they look at. They tested this method on two different kinds of machine and showed that it works really well. |
Keywords
* Artificial intelligence * Anomaly detection
