Copertina

MirrorCheck: Efficient Adversarial Defense for Vision-Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Fares, Samar, Ziu, Klea, Aremu, Toluwani, Durasov, Nikita, Takáč, Martin, Fua, Pascal, Laptev, Ivan, Nandakumar, Karthik
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Redefining Contributions: Shapley-Driven Federated Learning
di: Tastan, Nurbek, et al.
Pubblicazione: (2024)

Diffusion Models are Secretly Zero-Shot 3DGS Harmonizers
di: Skorokhodov, Vsevolod, et al.
Pubblicazione: (2025)

ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference
di: Durasov, Nikita, et al.
Pubblicazione: (2022)

SPDMark: Selective Parameter Displacement for Robust Video Watermarking
di: Fares, Samar, et al.
Pubblicazione: (2025)

MOLM: Mixture of LoRA Markers
di: Fares, Samar, et al.
Pubblicazione: (2025)

IT$^3$: Idempotent Test-Time Training
di: Durasov, Nikita, et al.
Pubblicazione: (2024)

Uncertainty Estimation for 3D Object Detection via Evidential Learning
di: Durasov, Nikita, et al.
Pubblicazione: (2024)

$ψ$DAG: Projected Stochastic Approximation Iteration for DAG Structure Learning
di: Ziu, Klea, et al.
Pubblicazione: (2024)

Thinking like a CHEMIST: Combined Heterogeneous Embedding Model Integrating Structure and Tokens
di: Rekut, Nikolai, et al.
Pubblicazione: (2025)

WaveSSM: Multiscale State-Space Models for Non-stationary Signal Attention
di: Solozabal, Ruben, et al.
Pubblicazione: (2026)

Enabling Uncertainty Estimation in Iterative Neural Networks
di: Durasov, Nikita, et al.
Pubblicazione: (2024)

Optimizing Adaptive Attacks against Watermarks for Language Models
di: Diaa, Abdulrahman, et al.
Pubblicazione: (2024)

VALD: Multi-Stage Vision Attack Detection for Efficient LVLM Defense
di: Kadvil, Nadav, et al.
Pubblicazione: (2026)

Multi-Attribute Vision Transformers are Efficient and Robust Learners
di: Gani, Hanan, et al.
Pubblicazione: (2024)

Watermarking Should Be Treated as a Monitoring Primitive
di: Aremu, Toluwani, et al.
Pubblicazione: (2026)

VecHeart: Holistic Four-Chamber Cardiac Anatomy Modeling via Hybrid VecSets
di: Chen, Yihong, et al.
Pubblicazione: (2026)

Robust Safety Monitoring of Language Models via Activation Watermarking
di: Aremu, Toluwani, et al.
Pubblicazione: (2026)

Adversarial Defense in Vision-Language Models: An Overview
di: Fu, Xiaowei, et al.
Pubblicazione: (2026)

DataCook: Crafting Anti-Adversarial Examples for Healthcare Data Copyright Protection
di: Shang, Sihan, et al.
Pubblicazione: (2024)

Do you understand epistemic uncertainty? Think again! Rigorous frequentist epistemic uncertainty estimation in regression
di: Foglia, Enrico, et al.
Pubblicazione: (2025)

Mitigating Watermark Forgery in Generative Models via Randomized Key Selection
di: Aremu, Toluwani, et al.
Pubblicazione: (2025)

Test-Time Low Rank Adaptation via Confidence Maximization for Zero-Shot Generalization of Vision-Language Models
di: Imam, Raza, et al.
Pubblicazione: (2024)

PromptSmooth: Certifying Robustness of Medical Vision-Language Models via Prompt Learning
di: Hussein, Noor, et al.
Pubblicazione: (2024)

PhysMoDPO: Physically-Plausible Humanoid Motion with Preference Optimization
di: Zhang, Yangsong, et al.
Pubblicazione: (2026)

Calibration-Aware Prompt Learning for Medical Vision-Language Models
di: Basu, Abhishek, et al.
Pubblicazione: (2025)

RECALL: Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles
di: Nwadike, Munachiso, et al.
Pubblicazione: (2025)

No Identity, no problem: Motion through detection for people tracking
di: Engilberge, Martin, et al.
Pubblicazione: (2024)

CLOAF: CoLlisiOn-Aware Human Flow
di: Davydov, Andrey, et al.
Pubblicazione: (2024)

FedPeWS: Personalized Warmup via Subnetworks for Enhanced Heterogeneous Federated Learning
di: Tastan, Nurbek, et al.
Pubblicazione: (2024)

Probing the Efficacy of Federated Parameter-Efficient Fine-Tuning of Vision Transformers for Medical Image Classification
di: Alkhunaizi, Naif, et al.
Pubblicazione: (2024)

Model-agnostic Adversarial Attack and Defense for Vision-Language-Action Models
di: Xu, Haochuan, et al.
Pubblicazione: (2025)

AGORA: Adversarial Generation Of Real-time Animatable 3D Gaussian Head Avatars
di: Fazylov, Ramazan, et al.
Pubblicazione: (2025)

One Graph to Track Them All: Dynamic GNNs for Single- and Multi-View Tracking
di: Engilberge, Martin, et al.
Pubblicazione: (2025)

STEREO: A Two-Stage Framework for Adversarially Robust Concept Erasing from Text-to-Image Diffusion Models
di: Srivatsan, Koushik, et al.
Pubblicazione: (2024)

Addressing the Elephant in the Room: Robust Animal Re-Identification with Unsupervised Part-Based Feature Alignment
di: Yu, Yingxue, et al.
Pubblicazione: (2024)

A Hybrid Defense Strategy for Boosting Adversarial Robustness in Vision-Language Models
di: Liang, Yuhan, et al.
Pubblicazione: (2024)

Multimodal Adversarial Defense for Vision-Language Models by Leveraging One-To-Many Relationships
di: Waseda, Futa, et al.
Pubblicazione: (2024)

A Framework for Double-Blind Federated Adaptation of Foundation Models
di: Tastan, Nurbek, et al.
Pubblicazione: (2025)

Gradient Distance Function
di: Le, Hieu, et al.
Pubblicazione: (2024)

Garment Recovery with Shape and Deformation Priors
di: Li, Ren, et al.
Pubblicazione: (2023)