Soft Adversarial Training Can Retain Natural Accuracy
This work addresses the need for robust neural networks in moderately critical applications by balancing accuracy and robustness, though it is incremental as it builds on existing adversarial training methods.
The paper tackles the problem of adversarial training sacrificing natural accuracy by proposing a soft adversarial training framework that uses abstract certification to select a subset of inputs, aiming to retain natural accuracy without sacrificing robustness in constrained settings. The results demonstrate the effectiveness of this approach for defense against adversarial attacks.
Adversarial training for neural networks has been in the limelight in recent years. The advancement in neural network architectures over the last decade has led to significant improvement in their performance. It sparked an interest in their deployment for real-time applications. This process initiated the need to understand the vulnerability of these models to adversarial attacks. It is instrumental in designing models that are robust against adversaries. Recent works have proposed novel techniques to counter the adversaries, most often sacrificing natural accuracy. Most suggest training with an adversarial version of the inputs, constantly moving away from the original distribution. The focus of our work is to use abstract certification to extract a subset of inputs for (hence we call it 'soft') adversarial training. We propose a training framework that can retain natural accuracy without sacrificing robustness in a constrained setting. Our framework specifically targets moderately critical applications which require a reasonable balance between robustness and accuracy. The results testify to the idea of soft adversarial training for the defense against adversarial attacks. At last, we propose the scope of future work for further improvement of this framework.