A Geometric Probe of the Accuracy-Robustness Trade-off: Sharp Boundaries in Symmetry-Breaking Dimensional Expansion
The trade-off between clean accuracy and adversarial robustness is a pervasive phenomenon in deep learning, yet its geometric origin remains elusive. In this work, we utilize Symmetry-Breaking Dimensional Expansion (SBDE) as a controlled probe to investigate the mechanism underlying this trade-off. SBDE expands input images by inserting constant-valued pixels, which breaks translational symmetry and consistently improves clean accuracy (e.g., from $90.47\%$ to $95.63\%$ on CIFAR-10 with ResNet-18) by reducing parameter degeneracy. However, this accuracy gain comes at the cost of reduced robustness against iterative white-box attacks. By employing a test-time \emph{mask projection} that resets the inserted auxiliary pixels to their training values, we demonstrate that the vulnerability stems almost entirely from the inserted dimensions. The projection effectively neutralizes the attacks and restores robustness, revealing that the model achieves high accuracy by creating \emph{sharp boundaries} (steep loss gradients) specifically along the auxiliary axes. Our findings provide a concrete geometric explanation for the accuracy-robustness paradox: the optimization landscape deepens the basin of attraction to improve accuracy but inevitably erects steep walls along the auxiliary degrees of freedom, creating a fragile sensitivity to off-manifold perturbations.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessResults from the Paper
| Rank | Task | Dataset | Model | Metrics |
|---|---|---|---|---|
| #1 | Adversarial Robustness | CIFAR-10 | A Geometric Probe of the Accuracy-Robust | Accuracy: 95.63 |
Similar Papers 제목 키워드 기반
The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Models
Fine-tuning approaches for Vision-Language Models (VLMs) face a critical three-way trade-off between In-Distribution (ID) accuracy, Out-of-Distribution (OOD) generalization, and adversarial robustness. Existing robust fi…
Adversarial RobustnessHow Sharp and Bias-Robust is a Model? Dual Evaluation Perspectives on Knowledge Graph Completion
Knowledge graph completion (KGC) aims to predict missing facts from the observed KG. While a number of KGC models have been studied, the evaluation of KGC still remain underexplored. In this paper, we observe that existi…
Knowledge Graph CompletionSharpness-Aware Minimization Alone can Improve Adversarial Robustness
Sharpness-Aware Minimization (SAM) is an effective method for improving generalization ability by regularizing loss sharpness. In this paper, we explore SAM in the context of adversarial robustness. We find that using on…
Adversarial RobustnessMathematical ProofsThe Condition-Number Principle for Prototype Clustering
We develop a geometric framework that links objective accuracy to structural recovery in prototype-based clustering. The analysis is algorithm-agnostic and applies to a broad class of admissible loss functions. We define…
PROBE-Web: An Interactive System for Probing Evaluation Landscapes of Knowledge Graph Completion Models
Knowledge graph completion (KGC) models are commonly evaluated using rank-based metrics such as MRR and Hits@K, despite different users often requiring different evaluation perspectives. In this demo, we present PROBE-We…
Knowledge Graph Completion