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.
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.
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.
Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e. g.
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.
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).
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...
arXiv:2512. 12997v2 Announce Type: replace-cross Abstract: CLIP delivers strong zero-shot classification but remains highly vulnerable to adversarial attacks.
arXiv:2505.12912v2 Announce Type: replace Abstract: Pre-trained vision-language models, such as contrastive language-image pre-training (CLIP), have demonstrated a remarkable generalizability, enabli...
arXiv:2608. 18339v1 Announce Type: cross Abstract: Vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities yet remain sensitive to real-world distribution shifts during inference.
arXiv:2504. 14798v2 Announce Type: replace Abstract: Machine Unlearning (MUL) has emerged as a key mechanism for privacy protection and content regulation, yet current techniques often fail to guarantee the complete removal of sensitive information.
While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks. Existing defense methods predominantly target single-task scenarios (e.
arXiv:2606. 10571v1 Announce Type: cross Abstract: Adversarial examples reveal vulnerabilities in Vision-Language Pre-training (VLP) models and provide insights for improving robustness.