Anchoring Adversarial Trajectories to Data Manifolds: A Bilevel Transfer Optimization Framework
cs.LG, cs.CR, cs.CV
Submitted: 2026-09-30
Updated: 2026-09-30
Comments: Accepted at NeurIPS 2026 as a Spotlight. 21 pages, 6 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Countering Adversarial Images using Input Transformations
- Back to Basics: Let Denoising Generative Models Denoise
- Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks
- Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
- Ensemble Adversarial Training: Attacks and Defenses
- Boosting Adversarial Transferability through Enhanced Momentum
- Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features
- Mitigating Adversarial Effects Through Randomization
- Diffusion Subgoal Planning for Long-Horizon Offline Goal-Conditioned Reinforcement Learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks