Cover Image

Latent Danger Zone: Distilling Unified Attention for Cross-Architecture Black-box Attacks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Yang, Wang, Chenyu, Wang, Tingrui, Wang, Yongwei, Li, Haonan, Liu, Zhunga, Pan, Quan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DOEPatch: Dynamically Optimized Ensemble Model for Adversarial Patches Generation
by: Tan, Wenyi, et al.
Published: (2023)

Flexible Physical Camouflage Generation Based on a Differential Approach
by: Li, Yang, et al.
Published: (2024)

Cross-Resolution Distribution Matching for Diffusion Distillation
by: Chen, Feiyang, et al.
Published: (2026)

Monocular Obstacle Avoidance Based on Inverse PPO for Fixed-wing UAVs
by: Chai, Haochen, et al.
Published: (2024)

Collaborative Learning of Scattering and Deep Features for SAR Target Recognition with Noisy Labels
by: Fu, Yimin, et al.
Published: (2025)

Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack
by: Diao, Yunfeng, et al.
Published: (2022)

Universal Multi-view Black-box Attack against Object Detectors via Layout Optimization
by: Wang, Donghua, et al.
Published: (2024)

BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
by: Cheng, Zhiyuan, et al.
Published: (2024)

MCN-CL: Multimodal Cross-Attention Network and Contrastive Learning for Multimodal Emotion Recognition
by: Li, Feng, et al.
Published: (2025)

Rethinking Representations for Cross-Domain Infrared Small Target Detection: A Generalizable Perspective from the Frequency Domain
by: Fu, Yimin, et al.
Published: (2026)

MakeupAttack: Feature Space Black-box Backdoor Attack on Face Recognition via Makeup Transfer
by: Sun, Ming, et al.
Published: (2024)

Evolving from Unknown to Known: Retentive Angular Representation Learning for Incremental Open Set Recognition
by: Yang, Runqing, et al.
Published: (2025)

Promoting CNNs with Cross-Architecture Knowledge Distillation for Efficient Monocular Depth Estimation
by: Zheng, Zhimeng, et al.
Published: (2024)

Black-box Adversarial Attacks Against Image Quality Assessment Models
by: Ran, Yu, et al.
Published: (2024)

Black-box Membership Inference Attacks on the Pre-training Data of Image-generation Models
by: Qi, Tao, et al.
Published: (2026)

MST-Distill: Mixture of Specialized Teachers for Cross-Modal Knowledge Distillation
by: Li, Hui, et al.
Published: (2025)

Scaling Laws for Black box Adversarial Attacks
by: Liu, Chuan, et al.
Published: (2024)

Revealing Vulnerabilities in Stable Diffusion via Targeted Attacks
by: Zhang, Chenyu, et al.
Published: (2024)

ArtiLatent: Realistic Articulated 3D Object Generation via Structured Latents
by: Chen, Honghua, et al.
Published: (2025)

ZQBA: Zero Query Black-box Adversarial Attack
by: Costa, Joana C., et al.
Published: (2025)

FSPGD: Rethinking Black-box Attacks on Semantic Segmentation
by: Park, Eun-Sol, et al.
Published: (2025)

A Multimodal Dangerous State Recognition and Early Warning System for Elderly with Intermittent Dementia
by: Deng, Liyun, et al.
Published: (2024)

Out-of-the-box: Black-box Causal Attacks on Object Detectors
by: Navaratnarajah, Melane, et al.
Published: (2025)

Reward Guided Latent Consistency Distillation
by: Li, Jiachen, et al.
Published: (2024)

Black-box Targeted Adversarial Attack on Segment Anything (SAM)
by: Zheng, Sheng, et al.
Published: (2023)

Multi-modal Relation Distillation for Unified 3D Representation Learning
by: Wang, Huiqun, et al.
Published: (2024)

Fine-Grained Prototypes Distillation for Few-Shot Object Detection
by: Wang, Zichen, et al.
Published: (2024)

RNAS-CL: Robust Neural Architecture Search by Cross-Layer Knowledge Distillation
by: Nath, Utkarsh, et al.
Published: (2023)

SWARD: Stochastic Window-Attention-Based Relational Distillation for Cross-Architectural Semantic Segmentation
by: Makineni, Aditya, et al.
Published: (2026)

Latent Video Dataset Distillation
by: Li, Ning, et al.
Published: (2025)

Stable Score Distillation
by: Zhu, Haiming, et al.
Published: (2025)

Practical No-box Adversarial Attacks with Training-free Hybrid Image Transformation
by: Zhang, Qilong, et al.
Published: (2022)

NoPain: No-box Point Cloud Attack via Optimal Transport Singular Boundary
by: Li, Zezeng, et al.
Published: (2025)

Attention Distillation: A Unified Approach to Visual Characteristics Transfer
by: Zhou, Yang, et al.
Published: (2025)

Delving into Decision-based Black-box Attacks on Semantic Segmentation
by: Chen, Zhaoyu, et al.
Published: (2024)

Prototypical Distillation and Debiased Tuning for Black-box Unsupervised Domain Adaptation
by: Liang, Jian, et al.
Published: (2024)

LatentUMM: Dual Latent Alignment for Unified Multimodal Models
by: Luo, Yinyi, et al.
Published: (2026)

Shedding Light on VLN Robustness: A Black-box Framework for Indoor Lighting-based Adversarial Attack
by: Li, Chenyang, et al.
Published: (2025)

Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection
by: Yang, Longrong, et al.
Published: (2023)

Cross-Architecture Distillation Made Simple with Redundancy Suppression
by: Zhang, Weijia, et al.
Published: (2025)