Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets

TL;DR

This paper introduces a novel framework for multi-target robustness in deep learning by modeling adversarial defenses as a bargaining game, using adaptive budgets to prevent player domination and improve robustness against multiple attacks.

Contribution

It proposes a new bargaining game perspective and an adaptive budget mechanism to enhance multi-target robustness, addressing limitations of existing max-based approaches.

Findings

Significant improvement in multi-target robustness on benchmark datasets.

Identification of player domination as a key issue in existing methods.

Theoretical analysis supports the effectiveness of adaptive budgets.

Abstract

Despite incredible advances, deep learning has been shown to be susceptible to adversarial attacks. Numerous approaches have been proposed to train robust networks both empirically and certifiably. However, most of them defend against only a single type of attack, while recent work takes steps forward in defending against multiple attacks. In this paper, to understand multi-target robustness, we view this problem as a bargaining game in which different players (adversaries) negotiate to reach an agreement on a joint direction of parameter updating. We identify a phenomenon named player domination in the bargaining game, namely that the existing max-based approaches, such as MAX and MSD, do not converge. Based on our theoretical analysis, we design a novel framework that adjusts the budgets of different adversaries to avoid any player dominance. Experiments on standard benchmarks show that employing the proposed framework to the existing approaches significantly advances multi-target robustness.