arXiv AI September 1, 2026 By Mingkun Zhang, Keping Bi, Wei Chen, Jiafeng Guo, Xueqi Cheng

CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification

The paper introduces CLIPure, a method for building an adversarially robust zero‑shot image classifier by purifying inputs in the latent space of CLIP. It formulates purification risk using KL divergence between denoising and attack processes via bidirectional SDEs, and proposes two variants: CLIPure‑Diff, which uses a diffusion prior, and CLIPure‑Cos, which relies on cosine similarity. Experiments on CIFAR‑10, ImageNet, and 13 other datasets show significant robustness gains, raising state‑of‑the‑art performance from 71.7% to 91.1% on CIFAR‑10 and from 59.6% to 72.6% on ImageNet.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Aug 12

Demystifying Adversarial Robustness in Diffusion Models: Compression, Randomness, and Geometry

arXiv:2505. 22839v2 Announce Type: replace-cross Abstract: Recent studies suggest that diffusion models significantly improve the empirical adversarial robustness of deep neural network models.

By Liu Yuezhang, Xue-Xin Wei

diffusion safety

arXiv AI

Jun 11

Diffusion-based Cumulative Adversarial Purification for Vision Language Models

arXiv:2506. 03933v2 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown remarkable capabilities in multimodal understanding, yet their susceptibility to adversarial perturbations poses a significant threat to their reliability in real-world applications.

By Jia Fu, Yongtao Wu, Yihang Chen, Kunyu Peng, Xiao Zhang, Volkan Cevher, Sepideh Pashami, Anders Holst

llms rag diffusion multimodal safety

Hugging Face Trending Papers

Jun 2

Investigating Adversarial Robustness of Multi-modal Large Language Models

Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e. g.

llms rag fine-tuning multimodal safety

arXiv Machine Learning

Aug 5

Adversarial Purification by Consistency-aware Latent Space Optimization on Data Manifolds

arXiv:2412. 08394v2 Announce Type: replace Abstract: Deep neural networks (DNNs) are vulnerable to adversarial samples crafted by adding imperceptible perturbations to clean data, potentially leading to incorrect and dangerous predictions.

By Shuhai Zhang, Jiahao Yang, Hui Luo, Jie Chen, Li Wang, Feng Liu, Bo Han, Mingkui Tan

diffusion safety

Hugging Face Trending Papers

Jun 29

A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP

Adversarial attacks pose a challenge to the reliability of deep learning models, motivating effective detection methods. Existing techniques often rely on attack-specific assumptions, access to adversarial samples, or knowledge of the underlying classifier (white-box).

rag benchmarks safety

arXiv Computer Vision

Aug 25

AdaptPrompt: Parameter-Efficient Adaptation of VLMs for Generalizable Deepfake Detection

arXiv:2512.17730v2 Announce Type: replace Abstract: Detectors of AI-generated images tend to inherit the biases of the data they are trained on: models fitted to GAN imagery learn to treat GAN-specif...

By Yichen Jiang, Mohammed Talha Alam, Sohail Ahmed Khan, Duc-Tien Dang-Nguyen, Fakhri Karray

llms diffusion fine-tuning benchmarks safety