Summary of Discerning the Chaos: Detecting Adversarial Perturbations While Disentangling Intentional From Unintentional Noises, by Anubhooti Jain et al.
Discerning the Chaos: Detecting Adversarial Perturbations while Disentangling Intentional from Unintentional Noises
by Anubhooti Jain, Susim Roy, Kwanit Gupta, Mayank Vatsa, Richa Singh
First submitted to arxiv on: 29 Sep 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
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 introduces CIAI, a Class-Independent Adversarial Intent detection network that detects both intentional and unintentional noise in deep learning models. The novel loss function combines Maximum Mean Discrepancy and Center Loss to identify manipulations like Gaussian and impulse noise. Trained in a multi-step fashion, CIAI is evaluated on five datasets (CelebA, CelebA-HQ, LFW, AgeDB, and CIFAR-10) against various attacks (FGSM, PGD, DeepFool, Gaussian, and Salt & Pepper noises). The proposed detector effectively detects both intentional and unintentional perturbations. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a new way to keep deep learning models safe from bad things people can do to them. They make a special tool called CIAI that finds when someone is trying to trick the model or if something just happens accidentally. This tool uses a special formula to figure out what’s going on and it works well with lots of different pictures. |
Keywords
» Artificial intelligence » Deep learning » Intent detection » Loss function
