Summary of Adba:approximation Decision Boundary Approach For Black-box Adversarial Attacks, by Feiyang Wang et al.
ADBA:Approximation Decision Boundary Approach for Black-Box Adversarial Attacks
by Feiyang Wang, Xingquan Zuo, Hai Huang, Gang Chen
First submitted to arxiv on: 7 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
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 In this paper, researchers introduce a novel approach to defend against decision-based black-box attacks on machine learning models. The proposed method, called Approximation Decision Boundary (ADB), efficiently and accurately compares perturbation directions without precisely determining decision boundaries. This is achieved by analyzing the probability distribution of decision boundaries and using the median value as ADB. The effectiveness of this method is demonstrated through extensive experiments on six well-known image classifiers, showing that it outperforms multiple state-of-the-art black-box attacks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps to protect machine learning models from being attacked by malicious data. It presents a new way to defend against attacks called decision-based black-box attacks. These attacks are very good at tricking the model into making mistakes. The researchers created a new algorithm that can quickly tell if an attack is coming and stop it. This makes it harder for attackers to fool the model. |
Keywords
» Artificial intelligence » Machine learning » Probability
