On the Computational Entanglement of Distant Features in Adversarial Machine Learning
In this research, we introduce the concept of "computational entanglement," a phenomenon observed in overparameterized feedforward linear networks that enables the network to achieve zero loss by fitting random noise, even on previously unseen test samples. Analyzing this behavior through spacetime diagrams reveals its connection to length contraction, where both training and test samples converge toward a shared normalized point within a flat Riemannian manifold. Moreover, we present a novel application of computational entanglement in transforming a worst-case adversarial examples-inputs that are highly non-robust and uninterpretable to human observers-into outputs that are both recognizable and robust. This provides new insights into the behavior of non-robust features in adversarial example generation, underscoring the critical role of computational entanglement in enhancing model robustness and advancing our understanding of neural networks in adversarial contexts.
Code (1)
Similar Papers 제목 키워드 기반
StyleID: Identity Disentanglement for Anonymizing Faces
Privacy of machine learning models is one of the remaining challenges that hinder the broad adoption of Artificial Intelligent (AI). This paper considers this problem in the context of image datasets containing faces. An…
DisentanglementGenerative Adversarial NetworkDecoder-free Robustness Disentanglement without (Additional) Supervision
Adversarial Training (AT) is proposed to alleviate the adversarial vulnerability of machine learning models by extracting only robust features from the input, which, however, inevitably leads to severe accuracy reduction…
BIG-bench Machine LearningDecoderDisentanglementRepresentation LearningQShield: Securing Neural Networks Against Adversarial Attacks using Quantum Circuits
Deep neural networks remain highly vulnerable to adversarial perturbations, limiting their reliability in security- and safety-critical applications. To address this challenge, we introduce QShield, a modular hybrid quan…
Adversarial RobustnessDetecting quantum entanglement with unsupervised learning
Quantum properties, such as entanglement and coherence, are indispensable resources in various quantum information processing tasks. However, there still lacks an efficient and scalable way to detecting these useful feat…
AFD: Mitigating Feature Gap for Adversarial Robustness by Feature Disentanglement
Adversarial fine-tuning methods enhance adversarial robustness via fine-tuning the pre-trained model in an adversarial training manner. However, we identify that some specific latent features of adversarial samples are c…
Adversarial RobustnessDisentanglement