ANCHOR: Integrating Adversarial Training with Hard-mined Supervised Contrastive Learning for Robust Representation Learning
This work addresses the vulnerability of neural networks to adversarial attacks, which is a critical security issue for AI systems in domains like image recognition, though it appears incremental as it builds on existing adversarial training and contrastive learning methods.
The paper tackles the problem of adversarial attacks on neural networks by proposing ANCHOR, a framework that integrates adversarial training with supervised contrastive learning and hard positive mining, achieving improved clean and robust accuracy on CIFAR-10 under PGD-20 attacks.
Neural networks have changed the way machines interpret the world. At their core, they learn by following gradients, adjusting their parameters step by step until they identify the most discriminant patterns in the data. This process gives them their strength, yet it also opens the door to a hidden flaw. The very gradients that help a model learn can also be used to produce small, imperceptible tweaks that cause the model to completely alter its decision. Such tweaks are called adversarial attacks. These attacks exploit this vulnerability by adding tiny, imperceptible changes to images that, while leaving them identical to the human eye, cause the model to make wrong predictions. In this work, we propose Adversarially-trained Contrastive Hard-mining for Optimized Robustness (ANCHOR), a framework that leverages the power of supervised contrastive learning with explicit hard positive mining to enable the model to learn representations for images such that the embeddings for the images, their augmentations, and their perturbed versions cluster together in the embedding space along with those for other images of the same class while being separated from images of other classes. This alignment helps the model focus on stable, meaningful patterns rather than fragile gradient cues. On CIFAR-10, our approach achieves impressive results for both clean and robust accuracy under PGD-20 (epsilon = 0.031), outperforming standard adversarial training methods. Our results indicate that combining adversarial guidance with hard-mined contrastive supervision helps models learn more structured and robust representations, narrowing the gap between accuracy and robustness.