Copertina

One Perturbation, Two Failure Modes: Probing VLM Safety via Embedding-Guided Typographic Perturbations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Balakrishnan, Ravikumar, Mendapara, Sanket
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models
di: Balakrishnan, Ravikumar, et al.
Pubblicazione: (2026)

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models
di: Balakrishnan, Ravikumar, et al.
Pubblicazione: (2025)

VISOR: Visual Input-based Steering for Output Redirection in Vision-Language Models
di: Phute, Mansi, et al.
Pubblicazione: (2025)

Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Model
di: Cheng, Hao, et al.
Pubblicazione: (2024)

More Images, More Problems? A Controlled Analysis of VLM Failure Modes
di: Das, Anurag, et al.
Pubblicazione: (2026)

VLM-SlideEval: Evaluating VLMs on Structured Comprehension and Perturbation Sensitivity in PPT
di: Kang, Hyeonsu, et al.
Pubblicazione: (2025)

APPLE: Adversarial Privacy-aware Perturbations on Latent Embedding for Unfairness Mitigation
di: Xu, Zikang, et al.
Pubblicazione: (2024)

JaiLIP: Jailbreaking Vision-Language Models via Loss Guided Image Perturbation
di: Mia, Md Jueal, et al.
Pubblicazione: (2025)

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models
di: Fang, Hao, et al.
Pubblicazione: (2024)

Defending Deepfake via Texture Feature Perturbation
di: Zhang, Xiao, et al.
Pubblicazione: (2025)

Fighting Hallucinations with Counterfactuals: Diffusion-Guided Perturbations for LVLM Hallucination Suppression
di: Dastmalchi, Hamidreza, et al.
Pubblicazione: (2026)

Causally Guided Gaussian Perturbations for Out-Of-Distribution Generalization in Medical Imaging
di: Pei, Haoran, et al.
Pubblicazione: (2025)

Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation
di: Jia, Sihang, et al.
Pubblicazione: (2026)

Typographic Text Generation with Off-the-Shelf Diffusion Model
di: Peong, KhayTze, et al.
Pubblicazione: (2024)

Automatic Text Box Placement for Supporting Typographic Design
di: Muraoka, Jun, et al.
Pubblicazione: (2025)

Not All Regions Are Equal: Attention-Guided Perturbation Network for Industrial Anomaly Detection
di: Huang, Tingfeng, et al.
Pubblicazione: (2024)

Adaptive Perturbation for Adversarial Attack
di: Yuan, Zheng, et al.
Pubblicazione: (2021)

Enhancing Generalization in Medical Visual Question Answering Tasks via Gradient-Guided Model Perturbation
di: Liu, Gang, et al.
Pubblicazione: (2024)

Visual-Friendly Concept Protection via Selective Adversarial Perturbations
di: Mi, Xiaoyue, et al.
Pubblicazione: (2024)

Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detection
di: Tan, Xiaofeng, et al.
Pubblicazione: (2024)

Morphologically Intelligent Perturbation Prediction with FORM
di: Naidoo, Reed, et al.
Pubblicazione: (2025)

Beyond Pixels: Semantic-aware Typographic Attack for Geo-Privacy Protection
di: Zhu, Jiayi, et al.
Pubblicazione: (2025)

Fight Perturbations with Perturbations: Defending Adversarial Attacks via Neuron Influence
di: Chen, Ruoxi, et al.
Pubblicazione: (2021)

PPEDCRF: Dynamic-CRF-Guided Selective Perturbation for Background-Based Location Privacy in Video Sequences
di: Ma, Bo, et al.
Pubblicazione: (2026)

AegisRF: Adversarial Perturbations Guided with Sensitivity for Protecting Intellectual Property of Neural Radiance Fields
di: Kim, Woo Jae, et al.
Pubblicazione: (2025)

Text-Guided Channel Perturbation and Pretrained Knowledge Integration for Unified Multi-Modality Image Fusion
di: Li, Xilai, et al.
Pubblicazione: (2025)

IDperturb: Enhancing Variation in Synthetic Face Generation via Angular Perturbation
di: Boutros, Fadi, et al.
Pubblicazione: (2026)

Adversarial Attacks on Robot Localization Systems via Deep Feature Perturbation
di: Li, Zhenyu, et al.
Pubblicazione: (2026)

Disruptive Attacks on Face Swapping via Low-Frequency Perceptual Perturbations
di: Huang, Mengxiao, et al.
Pubblicazione: (2025)

Removing Geometric Bias in One-Class Anomaly Detection with Adaptive Feature Perturbation
di: Hermary, Romain, et al.
Pubblicazione: (2025)

A Mimetic Detector for Adversarial Image Perturbations
di: Corbino, Johnny
Pubblicazione: (2026)

Wide Two-Layer Networks can Learn from Adversarial Perturbations
di: Kumano, Soichiro, et al.
Pubblicazione: (2024)

Spatial-Frequency Discriminability for Revealing Adversarial Perturbations
di: Wang, Chao, et al.
Pubblicazione: (2023)

Human Motion Prediction under Unexpected Perturbation
di: Yue, Jiangbei, et al.
Pubblicazione: (2024)

Texture Re-scalable Universal Adversarial Perturbation
di: Huang, Yihao, et al.
Pubblicazione: (2024)

GTPC-SSCD: Gate-guided Two-level Perturbation Consistency-based Semi-Supervised Change Detection
di: Xing, Yan, et al.
Pubblicazione: (2024)

ID-Eraser: Proactive Defense Against Face Swapping via Identity Perturbation
di: Luo, Junyan, et al.
Pubblicazione: (2026)

Defense against Unauthorized Distillation in Image Restoration via Feature Space Perturbation
di: Hu, Han, et al.
Pubblicazione: (2025)

Human-Object Interaction via Automatically Designed VLM-Guided Motion Policy
di: Deng, Zekai, et al.
Pubblicazione: (2025)

Adversarial Example Defense via Perturbation Grading Strategy
di: Zhu, Shaowei, et al.
Pubblicazione: (2022)