Copertina

VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional Spaces

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kumar, Somnath Sendhil, Govindarajulu, Yuvaraj, Kulkarni, Pavan, Parmar, Manojkumar
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

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies
di: Parmar, Manojkumar, et al.
Pubblicazione: (2025)

Enhancing TinyML Security: Study of Adversarial Attack Transferability
di: Shah, Parin, et al.
Pubblicazione: (2024)

MISLEAD: Manipulating Importance of Selected features for Learning Epsilon in Evasion Attack Deception
di: Khazanchi, Vidit, et al.
Pubblicazione: (2024)

AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling
di: Mai, Ziyang, et al.
Pubblicazione: (2026)

VidTAG: Temporally Aligned Video to GPS Geolocalization with Denoising Sequence Prediction at a Global Scale
di: Kulkarni, Parth Parag, et al.
Pubblicazione: (2026)

PruneVid: Visual Token Pruning for Efficient Video Large Language Models
di: Huang, Xiaohu, et al.
Pubblicazione: (2024)

DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-Domain
di: Liu, Jun, et al.
Pubblicazione: (2024)

UniVid: The Open-Source Unified Video Model
di: Luo, Jiabin, et al.
Pubblicazione: (2025)

Query-Efficient Hard-Label Black-Box Attack against Vision Transformers
di: Zhou, Chao, et al.
Pubblicazione: (2024)

IF-VidCap: Can Video Caption Models Follow Instructions?
di: Li, Shihao, et al.
Pubblicazione: (2025)

Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Models
di: Zhang, Yunbei, et al.
Pubblicazione: (2026)

Test-Time Hinting for Black-Box Vision-Language Models
di: Hou, Kaihua, et al.
Pubblicazione: (2026)

Box-Free Model Watermarks Are Prone to Black-Box Removal Attacks
di: An, Haonan, et al.
Pubblicazione: (2024)

VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding
di: He, Zhihao, et al.
Pubblicazione: (2026)

UniVid: Pyramid Diffusion Model for High Quality Video Generation
di: Xiao, Xinyu, et al.
Pubblicazione: (2026)

DynaVid: Learning to Generate Highly Dynamic Videos using Synthetic Motion Data
di: Jin, Wonjoon, et al.
Pubblicazione: (2026)

BlockVid: Block Diffusion for High-Quality and Consistent Minute-Long Video Generation
di: Zhang, Zeyu, et al.
Pubblicazione: (2025)

MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs
di: Ma, Junpeng, et al.
Pubblicazione: (2025)

HarmoVid: Relightful Video Portrait Harmonization
di: Choi, Jun Myeong, et al.
Pubblicazione: (2026)

Opening the Black Box: Preliminary Insights into Affective Modeling in Multimodal Foundation Models
di: Zhang, Zhen, et al.
Pubblicazione: (2026)

Prime Once, then Reprogram Locally: An Efficient Alternative to Black-Box Service Model Adaptation
di: Zhang, Yunbei, et al.
Pubblicazione: (2026)

PPO-MI: Efficient Black-Box Model Inversion via Proximal Policy Optimization
di: Shou, Xinpeng
Pubblicazione: (2025)

Allegro: Open the Black Box of Commercial-Level Video Generation Model
di: Zhou, Yuan, et al.
Pubblicazione: (2024)

DiffExplainer: Unveiling Black Box Models Via Counterfactual Generation
di: Fang, Yingying, et al.
Pubblicazione: (2024)

Efficient Learning for Product Attributes with Compact Multimodal Models
di: Kulkarni, Mandar
Pubblicazione: (2025)

UniVid: Unifying Vision Tasks with Pre-trained Video Generation Models
di: Chen, Lan, et al.
Pubblicazione: (2025)

EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models
di: Huang, Shiqi, et al.
Pubblicazione: (2026)

VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models
di: Zhang, Zhicheng, et al.
Pubblicazione: (2025)

Federated Black-Box Adaptation for Semantic Segmentation
di: Paranjape, Jay N., et al.
Pubblicazione: (2024)

OpenVidVRD: Open-Vocabulary Video Visual Relation Detection via Prompt-Driven Semantic Space Alignment
di: Liu, Qi, et al.
Pubblicazione: (2025)

VidHal: Benchmarking Temporal Hallucinations in Vision LLMs
di: Choong, Wey Yeh, et al.
Pubblicazione: (2024)

Breaking the Black-Box: Confidence-Guided Model Inversion Attack for Distribution Shift
di: Liu, Xinhao, et al.
Pubblicazione: (2024)

Learning Instance-Specific Parameters of Black-Box Models Using Differentiable Surrogates
di: Khondaker, Arnisha, et al.
Pubblicazione: (2024)

Beyond Top Activations: Efficient and Reliable Crowdsourced Evaluation of Automated Interpretability
di: Oikarinen, Tuomas, et al.
Pubblicazione: (2025)

What Your Features Reveal: Data-Efficient Black-Box Feature Inversion Attack for Split DNNs
di: Ren, Zhihan, et al.
Pubblicazione: (2025)

OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
di: Nan, Kepan, et al.
Pubblicazione: (2024)

RealCam-Vid: High-resolution Video Dataset with Dynamic Scenes and Metric-scale Camera Movements
di: Zheng, Guangcong, et al.
Pubblicazione: (2025)

InstructVid2Vid: Controllable Video Editing with Natural Language Instructions
di: Qin, Bosheng, et al.
Pubblicazione: (2023)

VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding
di: Li, Chaoyu, et al.
Pubblicazione: (2024)

VidEoMT: Your ViT is Secretly Also a Video Segmentation Model
di: Norouzi, Narges, et al.
Pubblicazione: (2026)