CORTEXA
← Browse
arxivcs.CV2026-06-29

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

Hodaya Krakover, Meir Yossef Levi, Eyal Gofer, Guy Gilboa

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). We propose $A^4D$ Attack- and Architecture-Agnostic Adversarial Detector, a completely black-box, zero-shot adversarial attack detection framework that utilizes prompt-based similarity scores derived from CLIP. To the best of our knowledge this is the first attempt to utilize CLIP for such a task. The method is based on two key observations: (i) CLIP is sensitive even to small imperceptible non-semantic perturbations; (ii) The shift in CLIP embedding space is not arbitrary and can be used as a robust attack indicator. Experiments across multiple attacks, datasets and classifiers validate that $A^4D$ achieves SOTA detection results in the attack-agnostic and classifier-agnostic setting.

View free PDFSource page

Related papers

arxivcs.CVcs.AI2026-07-06

LipSSD: Lipschitz-Constrained Single-Shot Detection for Adversarially Robust Object Detection

Vincent Lébé, Yannick Prudent, Corentin Friedrich, Thomas Massena, Ronan Sicre, Franck Mamalet

Object detectors have many applications in safety-critical systems, but they are known to be sensitive to worst-case perturbations such as adversarial attacks, which limits their applicability in real-world scenarios. Compared with classification, adversarial robustness for objec…

View free PDFSource page
arxivcs.CV2026-07-06

DiCE-CIR: Direct Composition Learning for Efficient Zero-Shot Composed Image Retrieval

Gwang-Ho Na, Ho-Joong Kim, Seong-Whan Lee

Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image from a multimodal query consisting of a reference image and an edit text describing the desired modification. Recent ZS-CIR studies have relied on projection-based methods that map a reference image into…

View free PDFSource page
arxivcs.CV2026-07-17

When Can Test-Time Adaptation Help Zero-Shot CT Vision-Language Models?

Ailar Mahdizadeh, Puria Azadi Moghadam, Xiangteng He, Leonid Sigal

3D CT vision-language models (VLMs) classify abnormalities from text prompts in a zero-shot manner, enabling cross-institution deployment where labels are scarce and clinical tasks shift faster than supervised models can be retrained. A real CT scan, however, typically contains s…

View free PDFSource page
arxivcs.CV2026-07-10

Promptable Concept Segmentation from Above: Evaluating SAM 3's Zero-Shot and One-Shot Capabilities in Remote Sensing

Mohammad Dabaja, Turgay Celik

The deployment of large-scale foundation models, such as the Segment Anything Model 3 (SAM 3), promises a transition toward open-vocabulary, training-free computer vision. However, their capacity to generalize out-of-distribution to the complex, top-down geometric structures of E…

View free PDFSource page
arxivcs.CV2026-07-07

Progressive Reasoning with Primitive Correction for Compositional Zero-Shot Learning

Ziyi Chen, Haoyan Shi, Sunhan Xu, Congyan Lang

Compositional Zero-Shot Learning (CZSL) aims to combine known attributes and objects as primitives for recognizing previously unseen attribute-object pairs. Prior works either predict attributes and objects independently, missing their strong contextual dependency, or use unidire…

View free PDFSource page
arxivcs.CV2026-07-02

FlowCIR: Semantic Transport via Flow Matching for Zero-Shot Composed Image Retrieval

Zhenqi He, Ziqi Jiang, Yuanpei Liu, Yanghao Wang, Teng Wang, Long Chen

Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image by editing a reference image with a natural-language instruction, without relying on domain-specific annotated triplets. Most existing ZS-CIR methods rely on textual inversion to translate the reference i…

View free PDFSource page