Penny Wise, Pixel Foolish: Bypassing Price Constraints in Multimodal Agents via Visual Adversarial Perturbations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qian, Jiachen, Kang, Zhaolu
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Boosting Adversarial Transferability via Residual Perturbation Attack
by: Peng, Jinjia, et al.
Published: (2025)

Transcending Adversarial Perturbations: Manifold-Aided Adversarial Examples with Legitimate Semantics
by: Li, Shuai, et al.
Published: (2024)

Consistent Attack: Universal Adversarial Perturbation on Embodied Vision Navigation
by: Ying, Chengyang, et al.
Published: (2022)

GreedyPixel: Fine-Grained Black-Box Adversarial Attack Via Greedy Algorithm
by: Wang, Hanrui, et al.
Published: (2025)

Dissecting Adversarial Robustness of Multimodal LM Agents
by: Wu, Chen Henry, et al.
Published: (2024)

Sparse vs Contiguous Adversarial Pixel Perturbations in Multimodal Models: An Empirical Analysis
by: Botocan, Cristian-Alexandru, et al.
Published: (2024)

From Feature Visualization to Visual Circuits: Effect of Adversarial Model Manipulation
by: Nanfack, Geraldin, et al.
Published: (2024)

Enhancing Adversarial Example Detection Through Model Explanation
by: Ma, Qian, et al.
Published: (2025)

Bypassing LLM Watermarks with Color-Aware Substitutions
by: Wu, Qilong, et al.
Published: (2024)

Visual Exclusivity Attacks: Automatic Multimodal Red Teaming via Agentic Planning
by: Zhang, Yunbei, et al.
Published: (2026)

Continual Adversarial Defense
by: Wang, Qian, et al.
Published: (2023)

AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editing
by: Hong, Ziming, et al.
Published: (2025)

Deep Learning with Data Privacy via Residual Perturbation
by: Tao, Wenqi, et al.
Published: (2024)

Adversarial Defenses via Vector Quantization
by: Dong, Zhiyi, et al.
Published: (2023)

Pixel Seal: Adversarial-only training for invisible image and video watermarking
by: Souček, Tomáš, et al.
Published: (2025)

AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation
by: Peng, Heqi, et al.
Published: (2024)

Interpretation of Neural Networks is Susceptible to Universal Adversarial Perturbations
by: Oskouie, Haniyeh Ehsani, et al.
Published: (2022)

Penny-Wise and Pound-Foolish in Deepfake Detection
by: Wang, Yabin, et al.
Published: (2024)

Improving Transferability of Adversarial Examples via Bayesian Attacks
by: Li, Qizhang, et al.
Published: (2023)

Improving Adversarial Training using Vulnerability-Aware Perturbation Budget
by: Fakorede, Olukorede, et al.
Published: (2024)

GradID: Adversarial Detection via Intrinsic Dimensionality of Gradients
by: Razmjoo, Mohammad Mahdi, et al.
Published: (2025)

Enabling Heterogeneous Adversarial Transferability via Feature Permutation Attacks
by: Wu, Tao, et al.
Published: (2025)

Assessing Neural Network Robustness via Adversarial Pivotal Tuning
by: Christensen, Peter Ebert, et al.
Published: (2022)

Structure Disruption: Subverting Malicious Diffusion-Based Inpainting via Self-Attention Query Perturbation
by: He, Yuhao, et al.
Published: (2025)

Revisiting Transferable Adversarial Images: Systemization, Evaluation, and New Insights
by: Zhao, Zhengyu, et al.
Published: (2023)

Towards Model Resistant to Transferable Adversarial Examples via Trigger Activation
by: Yu, Yi, et al.
Published: (2025)

Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies
by: Bartoldson, Brian R., et al.
Published: (2024)

Attack Anything: Blind DNNs via Universal Background Adversarial Attack
by: Lian, Jiawei, et al.
Published: (2024)

Learning Differentially Private Diffusion Models via Stochastic Adversarial Distillation
by: Liu, Bochao, et al.
Published: (2024)

Adversarial Training against Location-Optimized Adversarial Patches
by: Rao, Sukrut, et al.
Published: (2020)

Beauty and the Beast: Imperceptible Perturbations Against Diffusion-Based Face Swapping via Directional Attribute Editing
by: Huang, Yilong, et al.
Published: (2026)

Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models
by: Xu, Jingyao, et al.
Published: (2024)

A Survey on Physical Adversarial Attacks against Face Recognition Systems
by: Wang, Mingsi, et al.
Published: (2024)

Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement
by: Yu, Daiwei, et al.
Published: (2024)

Ensemble Adversarial Defense via Integration of Multiple Dispersed Low Curvature Models
by: Zhao, Kaikang, et al.
Published: (2024)

Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness
by: Piras, Giorgio, et al.
Published: (2024)

Mitigating the Impact of Noisy Edges on Graph-Based Algorithms via Adversarial Robustness Evaluation
by: Wang, Yongyu, et al.
Published: (2024)

Exploring Adversarial Attacks against Latent Diffusion Model from the Perspective of Adversarial Transferability
by: Chen, Junxi, et al.
Published: (2024)

Beyond Full Poisoning: Effective Availability Attacks with Partial Perturbation
by: Zhe, Yu, et al.
Published: (2024)

Adversarial Sparse Teacher: Defense Against Distillation-Based Model Stealing Attacks Using Adversarial Examples
by: Yilmaz, Eda, et al.
Published: (2024)