Quantifying the Preferential Direction of the Model Gradient in Adversarial Training With Projected Gradient Descent
Adversarial training, especially projected gradient descent (PGD), has proven to be a successful approach for improving robustness against adversarial attacks. After adversarial training, gradients of models with respect to their inputs have a preferential direction. However, the direction of alignment is not mathematically well established, making it difficult to evaluate quantitatively. We propose a novel definition of this direction as the direction of the vector pointing toward the closest point of the support of the closest inaccurate class in decision space. To evaluate the alignment with this direction after adversarial training, we apply a metric that uses generative adversarial networks to produce the smallest residual needed to change the class present in the image. We show that PGD-trained models have a higher alignment than the baseline according to our definition, that our metric presents higher alignment values than a competing metric formulation, and that enforcing this alignment increases the robustness of models.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions
Adversarial examples are input examples that are specifically crafted to deceive machine learning classifiers. State-of-the-art adversarial example detection methods characterize an input example as adversarial either by…
Knowledge Gradient for Preference Learning
The knowledge gradient is a popular acquisition function in Bayesian optimization (BO) for optimizing black-box objectives with noisy function evaluations. Many practical settings, however, allow only pairwise comparison…
Info-Evo: Using Information Geometry to Guide Evolutionary Program Learning
A novel optimization strategy, Info-Evo, is described, in which natural gradient search using nonparametric Fisher information is used to provide ongoing guidance to an evolutionary learning algorithm, so that the evolut…
Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics
Since their introduction, Transformer architectures have dominated Natural Language Processing (NLP). However, recent research has highlighted an inherent anisotropy phenomenon in these models, presenting a significant c…
GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization
Recent advances in large language models have highlighted the critical need for precise control over model outputs through predefined constraints. While existing methods attempt to achieve this through either direct inst…
HallucinationPrompt Learning