Contrasting Adversarial Perturbations: The Space of Harmless Perturbations
Open Access
- 11 April 2025
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (2) , 2114-2122
Abstract
Existing works have extensively studied adversarial examples, which are minimal perturbations that can mislead the output of deep neural networks (DNNs) while remaining imperceptible to humans. However, in this work, we reveal the existence of a harmless perturbation space, in which perturbations drawn from this space, regardless of their magnitudes, leave the network output unchanged when applied to inputs. Essentially, the harmless perturbation space emerges from the usage of non-injective functions (linear or non-linear layers) within DNNs, enabling multiple distinct inputs to be mapped to the same output. For linear layers with input dimensions exceeding output dimensions, any linear combination of the orthogonal bases of the nullspace of the parameter consistently yields no change in their output. For non-linear layers, the harmless perturbation space may expand, depending on the properties of the layers and input samples. Inspired by this property of DNNs, we solve for a family of general perturbation spaces that are redundant for the DNN's decision, and can be used to hide sensitive data and serve as a means of model identification. Our work highlights the distinctive robustness of DNNs (i.e., consistency under large magnitude perturbations) in contrast to adversarial examples (vulnerability for small noises).Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- HuRef: HUman-REadable Fingerprint for Large Language Models2024
- TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIsIntelligent Computing, 2024
- Distance-Based Image Classification: Generalizing to New Classes at Near-Zero CostIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- The rank of a random matrixApplied Mathematics and Computation, 2007
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004