Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles
cs.CV, cs.AI, cs.LG
Submitted: 2025-10-03
Updated: 2026-11-06
Terminology
Sources
- Improving Adversarial Robustness via Channel-wise Activation Suppressing
- Curriculum Adversarial Training
- Towards Adversarially Robust and Domain Generalizable Stereo Matching by Rethinking DNN Feature Backbones
- Stochastic Activation Pruning for Robust Adversarial Defense
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Batch Normalization is a Cause of Adversarial Vulnerability
- Robust Decentralized Learning with Local Updates and Gradient Tracking
- Explaining and Harnessing Adversarial Examples
- Adversarial Logit Pairing
- Towards Deep Learning Models Resistant to Adversarial Attacks
- The 2017 DAVIS Challenge on Video Object Segmentation
- Translation Insensitive CNNs
- The Space of Transferable Adversarial Examples
- Test-time Detection and Repair of Adversarial Samples via Masked Autoencoder
- Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks
- Self-Ensemble Adversarial Training for Improved Robustness
- Enhancing Adversarial Defense by k-Winners-Take-All
- Test-time Adversarial Defense with Opposite Adversarial Path and High Attack Time Cost
- Wide Residual Networks
Related papers
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs
- From Formulas to Protocols: A Compositional View of Binary Target Segmentation Metrics
- Traffic Sign Recognition in Autonomous Driving: Dataset, Benchmark, and Field Experiment