REVIEW 7 cited by
Robust Classification via a Single Diffusion Model
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Diffusion models have been applied to improve adversarial robustness of image classifiers by purifying the adversarial noises or generating realistic data for adversarial training. However, diffusion-based purification can be evaded by stronger adaptive attacks while adversarial training does not perform well under unseen threats, exhibiting inevitable limitations of these methods. To better harness the expressive power of diffusion models, this paper proposes Robust Diffusion Classifier (RDC), a generative classifier that is constructed from a pre-trained diffusion model to be adversarially robust. RDC first maximizes the data likelihood of a given input and then predicts the class probabilities of the optimized input using the conditional likelihood estimated by the diffusion model through Bayes' theorem. To further reduce the computational cost, we propose a new diffusion backbone called multi-head diffusion and develop efficient sampling strategies. As RDC does not require training on particular adversarial attacks, we demonstrate that it is more generalizable to defend against multiple unseen threats. In particular, RDC achieves $75.67\%$ robust accuracy against various $\ell_\infty$ norm-bounded adaptive attacks with $\epsilon_\infty=8/255$ on CIFAR-10, surpassing the previous state-of-the-art adversarial training models by $+4.77\%$. The results highlight the potential of generative classifiers by employing pre-trained diffusion models for adversarial robustness compared with the commonly studied discriminative classifiers. Code is available at \url{https://github.com/huanranchen/DiffusionClassifier}.
Forward citations
Cited by 7 Pith papers
-
Revisiting Autoregressive Models for Generative Image Classification
Order-marginalized any-order AR models (RandAR) outperform diffusion generative classifiers on ImageNet and OOD sets and match strong SSL models at far lower cost.
-
Self-Improving Diffusion Classifiers with Minority Preference Optimization
Fine-tuning a diffusion model with a reconstruction-error minority reward via LoRA+GRPO improves zero-shot diffusion classification by expanding low-density coverage.
-
Evaluating Compositional Generalisation in VLMs and Diffusion Models
On the extended Concept Binding Benchmark, all tested VLMs, including the generative Diffusion Classifier, fail to distinguish left/right relations in generalised zero-shot settings, suggesting models rely on object r...
-
ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models
ZIUM attacks unlearned diffusion models by optimizing an image-captioning module that turns a target image into a text embedding, then reuses that module zero-shot on unseen images of the same unlearned concept.
-
CaO$_2$: Rectifying Inconsistencies in Diffusion-Based Dataset Distillation
CaO2 selects confident diffusion-generated samples and optimizes their latents against the denoising objective, achieving state-of-the-art distilled-dataset accuracy on ImageNet subsets.
-
NAPPure: Adversarial Purification for Robust Image Classification under Non-Additive Perturbations
By modeling the attack as a known transformation with unknown parameters, NAPPure jointly recovers the clean image and the perturbation through likelihood maximization, beating additive-only purification baselines on ...
-
Adaptive Routing for Efficient Diffusion Transformer-Based PNI Prediction
DiT-RC predicts cholangiocarcinoma PNI from tumor-centered 3D MRI with AUC 0.731 at 257.57 GFLOPs by routing attention heads, tokens, and MLP width in a diffusion classifier.
Discussion (0). Sign in to comment.