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.CV2026-07-31

VFAD: Variational Semantic Prompting Meets Frequency-Adaptive Representation Learning for Zero-Shot Anomaly Detection

Peng Chen, Kaige Li, Wei Wang, Mingbo Yang, Wenqiang Wang, Li Shen, et al.

Zero-shot anomaly detection (ZSAD) aims to detect and localize anomalies in unseen categories without access to target-specific training data. Although recent CLIP-based methods have demonstrated promising generalization through vision-language alignment, they remain limited in c…

View free PDFSource page
arxivcs.AIcs.CLcs.CVcs.RO2026-07-24

Zero-Shot Mission-Level Evaluation for Aerial MLLM Agents

Suman Navaratnarajah, Taehyoung Kim, Jona Ruthardt, Ishaan Bhimwal, Ryousuke Yamada, Yannik Blei, et al.

Multimodal Large Language Models (MLLMs) are emerging as core reasoning modules for embodied agents, yet it remains unclear how well general-purpose models can solve long-horizon embodied tasks from a single high-level instruction. We introduce MissionBench, a benchmark for missi…

View free PDFSource page
arxivcs.CV2026-07-23

GeoThreat: Transferable Targeted Adversarial Attacks on Large Vision-Language Models for Remote Sensing Image Interpretation

Yimin Fu, Yuefeng Bai, Baicheng Pan, Zhunga Liu, Michael K. Ng

Adversarial attacks against large vision-language models (LVLMs) serve as an effective means of assessing their robustness in cross-modal semantic understanding. Existing studies mainly focus on corrupting visual inputs to induce predefined erroneous responses in general vision-l…

View free PDFSource page
arxivcs.CV2026-07-31

Is It Time for the Renaissance of Salient Object Detection in the Era of MLLMs?

Wenzhuo Zhao, Xiuzhi Li, Zhongkuan Mao, Ronghao Xian, Yao Jiang, Zhao Gao, et al.

The zero-shot capabilities of multimodal large language models (MLLMs) are pushing salient object detection (SOD) beyond task-specific supervision. To disentangle MLLMs beyond conventional mask-based evaluation, we decompose SOD into localization and segmentation, and re-engineer…

View free PDFSource page
arxivcs.CV2026-07-23

DTIF: Robust Loop Closure Detection via Delaunay Triangle Topology in Complex Forests

Xin Zhao, Jianping Li, Qin Zou, Fuxun Liang, Zhen Dong, Bisheng Yang

Accurate forest inventory and large-scale mapping are essential for ecosystem monitoring and sustainable forest management. Multiple low-cost edge platforms enable efficient large-area data acquisition, but merging independently constructed local maps in GNSS-denied understory en…

View free PDFSource page
arxivcs.CV2026-07-23

Detectors Learn the Wrong Thing: Shortcut-Resistant Adversarial Training Against Physically Realizable Attacks

Yuanhao Huang, Yilong Ren, Jinlei Wang, Xuesong Bai, Zheng Zhang, Haiyang Yu

AI-enabled visual perception systems are increasingly deployed in intelligent transportation infrastructure and autonomous vehicle related applications. However, physically realizable adversarial appearances pose a significant reliability challenge for these safety-critical syste…

View free PDFSource page