Improving Adversarial Transferability via Model Alignment
Neural networks are susceptible to adversarial perturbations that are transferable across different models. In this paper, we introduce a novel model alignment technique aimed at improving a given source model's ability in generating transferable adversarial perturbations. During the alignment process, the parameters of the source model are fine-tuned to minimize an alignment loss. This loss measures the divergence in the predictions between the source model and another, independently trained model, referred to as the witness model. To understand the effect of model alignment, we conduct a geometric analysis of the resulting changes in the loss landscape. Extensive experiments on the ImageNet dataset, using a variety of model architectures, demonstrate that perturbations generated from aligned source models exhibit significantly higher transferability than those from the original source model.
Code (1)
Tasks
modelSimilar Papers 제목 키워드 기반
Boosting Adversarial Transferability with Spatial Adversarial Alignment
Deep neural networks are vulnerable to adversarial examples that exhibit transferability across various models. Numerous approaches are proposed to enhance the transferability of adversarial examples, including advanced …
Data AugmentationEvolving Architectures with Gradient Misalignment toward Low Adversarial Transferability
Deep neural network image classifiers are known to be susceptible not only to adversarial examples created for them but even those created for others. This phenomenon poses a potential security risk in various black-box …
Harmonizing Transferability and Discriminability for Adapting Object Detectors
Recent advances in adaptive object detection have achieved compelling results in virtue of adversarial feature adaptation to mitigate the distributional shifts along the detection pipeline. Whilst adversarial adaptation …
Objectobject-detectionObject DetectionWeakly Supervised Object DetectionImproving Adversarial Transferability in MLLMs via Dynamic Vision-Language Alignment Attack
Multimodal Large Language Models (MLLMs), built upon LLMs, have recently gained attention for their capabilities in image recognition and understanding. However, while MLLMs are vulnerable to adversarial attacks, the tra…
Rethinking Adversarial Transferability from a Data Distribution Perspective
Adversarial transferability enables attackers to generate adversarial examples from the source model to attack the target model, which has raised security concerns about the deployment of DNNs in practice. In this paper,…
Adversarial Attack