用GAN判别器检测图像数据中的恶意标签，精准识别污染样本。
Dirty and Clean-Label attack detection using GAN discriminators
- 用单类训练的GAN判别器分析图像异常，判断标签是否被篡改。
- 在扰动幅度ε≥0.20时，可100%识别测试中的污染样本。
- 无需重训模型，适合保护高价值视觉分类任务中的关键类别。
训练深度视觉模型需要大量图像，但来自不可信来源的数据可能引发脏标签或干净标签攻击，危及模型行为。手动检查每对图像-标签不现实，传统毒物检测需重训练模型，耗时。本研究利用训练于单一类别的GAN判别器，检测误标及不同程度修改的图像。同时对比了基础卷积神经网络在相同扰动下的表现。结果表明，在单类训练后，通过使用类内样本校准决策阈值，GAN判别器的置信度分数可在扰动幅度ε达到0.20时，100%识别出测试中的污染样本。该方法为开发者提供了一种无需重训即可保护关键类别免受数据污染的可行方案。
原文摘要 · Abstract (English)
Gathering enough images to train a deep computer vision model is a constant challenge. Unfortunately, collecting images from unknown sources can leave your model s behavior at risk of being manipulated by a dirty-label or clean-label attack unless the images are properly inspected. Manually inspecting each image-label pair is impractical and common poison-detection methods that involve re-training your model can be time consuming. This research uses GAN discriminators to protect a single class against mislabeled and different levels of modified images. The effect of said perturbation on a basic convolutional neural network classifier is also included for reference. The results suggest that after training on a single class, GAN discriminator s confidence scores can provide a threshold to identify mislabeled images and identify 100% of the tested poison starting at a perturbation epsilon magnitude of 0.20, after decision threshold calibration using in-class samples. Developers can use this report as a basis to train their own discriminators to protect high valued classes in their CV models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。