Research map / Adversarial robustness and security / Certified and empirical robustness

Adversary Aware Optimization for Robust Defense

NeurIPS 2025 · Adversarial robustness and security › Certified and empirical robustness · approach: Augmentation and diffusion purification · 0 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes an optimization-based adversarial purification framework that removes perturbations by maximizing a Bayesian-inspired objective combining a pretrained diffusion prior with an adversarial-perturbation likelihood term.

Problem

Deep neural networks are highly susceptible to adversarial attacks in which small, subtle input perturbations cause misclassification.

Approach

Instead of sampling-based diffusion purification, directly optimize the input to maximize a Bayesian-inspired objective that couples a pretrained diffusion prior with a likelihood term tailored to the adversarial perturbation space, thereby removing the perturbation.

Closest papers by meaning

• DiffHammer: Rethinking the Robustness of Diffusion-Based Adversarial Purification (NeurIPS 2024 · similarity 0.90)
• Instant Adversarial Purification with Adversarial Consistency Distillation (CVPR 2025 · similarity 0.90)
• Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective (ICLR 2025 · similarity 0.89)
• Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization (ICLR 2024 · similarity 0.89)
• Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM (CVPR 2024 · similarity 0.89)
• Adversarial Purification with the Manifold Hypothesis (AAAI 2024 · similarity 0.88)