Skip to content
Log in
Preprint

Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attacks

Yaohua Liu Yifan Guo Jiaxin Gao
Aug 2026 · 0 citations · 89 references
Computer Science

TL;DR

This work proposes BMAT (Bilevel-Minimax Adversarial Transfer), an integrated bottom-up solver that combines a Soft Weight Modulator and an Implicit Gradient Approximator to enable ternary coupling among initialization, surrogate adaptation, and perturbation optimization.

Abstract

Transfer-based adversarial attacks craft adversarial examples using surrogate models to mislead black-box victim models. Beyond perturbation generation, transferability is fundamentally governed by the coupling of initialization, surrogate adaptation, and gradient dynamics. We revisit this challenge from a bilevel-minimax perspective and propose BMAT (Bilevel-Minimax Adversarial Transfer). The bilevel formulation captures the dependency between initialization and perturbation, while the inner minimax problem promotes surrogate robustness for cross-architecture generalization. Algorithmically, we develop an integrated bottom-up solver that combines a Soft Weight Modulator and an Implicit Gradient Approximator to enable ternary coupling among initialization, surrogate adaptation, and perturbation optimization. We further provide theoretical insights into the optimization dynamics of the proposed bilevel-minimax framework. Extensive experiments on classification and segmentation benchmarks show that BMAT outperforms more than 10 strong baselines across more than 30 victim models, improving both intra- and cross-architecture transfer and yielding up to a 2x reduction in mIoU. Code is available at https://github.com/callous-youth/BMAT.

arXiv Semantic Scholar
View source

Similar papers

Aug 2026

Rethinking robust generalization with energy minimization.

Adversarial training has emerged as a leading strategy for enhancing the robustness of machine learning models against adversarial attacks. Its effectiveness often wanes when faced with unseen adversarial examples, resulting in suboptimal robust generalization. To address this issue, we introduce a novel energy-based optimization strategy to improve the robust generalization by incorporating the principles of energy-based models. Our framework models the energy of natural and adversarial examples, where natural samples are assigned to lower energy and adversarial samples to higher energy. During the inference phase, the influence of adversarial perturbation can be alleviated by energy minimization. Theoretically, we show that the proposed energy-based optimization strategy yields a tighter robust-generalization bound through an explicit energy-discrepancy term; this analysis provides an explanatory bound and should not be interpreted as certified robustness. Empirically, a series of evaluations provide evidence for the efficacy of the proposed methodology under the specified threat models and evaluation protocols, showing strong and competitive performance across three extensively utilized datasets. Specifically, EM-AT achieves 77.71% standard-AA robustness on CIFAR-10 and remains highly competitive under comparable lightweight settings. The source codes are available at https://github.com/LitterQ/EM-AT.

Zhuang Qian, Penglei Gao, Shufei Zhang et al. · 0 citations

Parameter-Efficient Dual-Loss Adaptation with Logit Divergence: A Unified Approach for Adversarial Example Detection and Robust Inference

D3Adapter is presented, a threat-aware framework that unifies adversarial example detection (AED) and robust inference and scalability across datasets with varying numbers of classes is studied, showing that unified detection and robust inference can be achieved with predictable overhead proportional to the number of adapters.

Zirui Fu, Marco Donato · 0 citations
Preprint Jul 2026

Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates

This work comprehensively investigates computation-efficient strategies to speed up latent adversarial training from two complementary perspectives, and reduces per-step adversarial-training FLOPs by 48.1% while requiring only 0.0118% trainable parameters.

Weiyi He, Yuping Lin, Jiliang Tang et al. · 0 citations

Diverge to Converge: Mutual Heterogeneous Learning for Robust Pruning

Mutual Heterogeneous Learning (MHL) is proposed, a framework enabling robust pruning via single-model inference that significantly outperforms single-model baselines in both adversarial robustness and corruption robustness, while maintaining competitive clean accuracy.

Jinhui Yu, Zikai Zhang, Khaled A. Harras et al. · 0 citations