Buchumschlag

Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Guan, Jiwei, Jin, Haibo, Wang, Haohan
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs
von: Basani, Advik Raj, et al.
Veröffentlicht: (2024)

Improving the Transferability of Adversarial Attacks by an Input Transpose
von: Wan, Qing, et al.
Veröffentlicht: (2025)

Towards Black-Box Membership Inference Attack for Diffusion Models
von: Li, Jingwei, et al.
Veröffentlicht: (2024)

DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models
von: Sun, Ye, et al.
Veröffentlicht: (2026)

On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
von: Zhang, Xinwei, et al.
Veröffentlicht: (2026)

SoK: Pitfalls in Evaluating Black-Box Attacks
von: Suya, Fnu, et al.
Veröffentlicht: (2023)

Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models
von: Souček, Tomáš, et al.
Veröffentlicht: (2025)

JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models
von: Jin, Haibo, et al.
Veröffentlicht: (2024)

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images
von: Stein, Kyle, et al.
Veröffentlicht: (2024)

Fingerprinting Image-to-Image Generative Adversarial Networks
von: Li, Guanlin, et al.
Veröffentlicht: (2021)

Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior
von: Cheng, Shuyu, et al.
Veröffentlicht: (2024)

L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attacks
von: Guo, Ping, et al.
Veröffentlicht: (2024)

Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters
von: Jin, Haibo, et al.
Veröffentlicht: (2024)

A White-Box False Positive Adversarial Attack Method on Contrastive Loss Based Offline Handwritten Signature Verification Models
von: Guo, Zhongliang, et al.
Veröffentlicht: (2023)

Rewriting the Budget: A General Framework for Black-Box Attacks Under Cost Asymmetry
von: Salmani, Mahdi, et al.
Veröffentlicht: (2025)

From Attack to Defense: Insights into Deep Learning Security Measures in Black-Box Settings
von: Juraev, Firuz, et al.
Veröffentlicht: (2024)

Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models
von: Zheng, Ziwei, et al.
Veröffentlicht: (2025)

Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters
von: Sarkar, Soumyendu, et al.
Veröffentlicht: (2025)

Standard-Deviation-Inspired Regularization for Improving Adversarial Robustness
von: Fakorede, Olukorede, et al.
Veröffentlicht: (2024)

Data-free Defense of Black Box Models Against Adversarial Attacks
von: Nayak, Gaurav Kumar, et al.
Veröffentlicht: (2022)

BB-Patch: BlackBox Adversarial Patch-Attack using Zeroth-Order Optimization
von: Kumar, Satyadwyoom, et al.
Veröffentlicht: (2024)

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

Undermining Image and Text Classification Algorithms Using Adversarial Attacks
von: Lunga, Langalibalele, et al.
Veröffentlicht: (2024)

PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks
von: Guo, Ping, et al.
Veröffentlicht: (2024)

Refusing Safe Prompts for Multi-modal Large Language Models
von: Shao, Zedian, et al.
Veröffentlicht: (2024)

Membership Inference Attacks against Large Vision-Language Models
von: Li, Zhan, et al.
Veröffentlicht: (2024)

Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial Hypervolume
von: Guo, Ping, et al.
Veröffentlicht: (2024)

Real-world Adversarial Defense against Patch Attacks based on Diffusion Model
von: Wei, Xingxing, et al.
Veröffentlicht: (2024)

CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing
von: Jin, Haibo, et al.
Veröffentlicht: (2021)

FC-Attack: Jailbreaking Multimodal Large Language Models via Auto-Generated Flowcharts
von: Zhang, Ziyi, et al.
Veröffentlicht: (2025)

SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images
von: Fan, Mingyuan, et al.
Veröffentlicht: (2024)

Adversarial Detection by Approximation of Ensemble Boundary
von: Windeatt, T.
Veröffentlicht: (2022)

Task-Agnostic Attacks Against Vision Foundation Models
von: Pulfer, Brian, et al.
Veröffentlicht: (2025)

Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?
von: Wang, Yanbo, et al.
Veröffentlicht: (2025)

On the Importance of Backbone to the Adversarial Robustness of Object Detectors
von: Li, Xiao, et al.
Veröffentlicht: (2023)

Evaluating the Evaluators: Trust in Adversarial Robustness Tests
von: Cinà, Antonio Emanuele, et al.
Veröffentlicht: (2025)

GLEAN: Generative Learning for Eliminating Adversarial Noise
von: Kim, Justin Lyu, et al.
Veröffentlicht: (2024)

The Impact of Scaling Training Data on Adversarial Robustness
von: Zimmerli, Marco, et al.
Veröffentlicht: (2025)

AR-GAN: Generative Adversarial Network-Based Defense Method Against Adversarial Attacks on the Traffic Sign Classification System of Autonomous Vehicles
von: Salek, M Sabbir, et al.
Veröffentlicht: (2023)

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