Calibrated Adversarial Sampling: Multi-Armed Bandit-Guided Generalization Against Unforeseen Attacks

The article discusses the challenges of deep neural networks, particularly focusing on transformation-based attacks that have shown success in transfer attacks. It highlights the limitations of existing methods, such as their reliance on low-iteration settings and uniform parameters across different models. The study proposes a new approach to dynamic parameter optimization to enhance the effectiveness of these attacks, addressing computational overhead and improving transferability across tasks.

The MOS Attack framework introduces a scalable approach to generating adversarial examples for Deep Neural Networks (DNNs). It addresses the limitations of existing single-objective adversarial attacks by leveraging multiple loss functions and their interrelations. This multi-objective optimization strategy allows for the incorporation of various loss functions without the need for additional parameters, enhancing the robustness evaluation of DNNs against adversarial attacks.

The article discusses the evaluation of Deep Neural Networks (DNNs) based on their generalization performance and robustness against adversarial attacks. It highlights the challenges in assessing DNNs solely through generalization metrics as their performance has reached state-of-the-art levels. The study introduces the concept of the Populated Region Set (PRS) to analyze the internal properties of DNNs that influence their robustness, revealing that a low PRS ratio correlates with improved adversarial robustness.