Cover Image

Capability and Robustness Cannot Both Be Free: An Information-Theoretic Bound for Vision-Language-Action Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Tai, Jianwei
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data
by: Zhang, Jie, et al.
Published: (2024)

State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space
by: Guo, Ji, et al.
Published: (2026)

Information Theoretic Adversarial Training of Large Language Models
by: Zhang, Yiwei, et al.
Published: (2026)

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI
by: Jin, Heng, et al.
Published: (2026)

CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models
by: Wan, Shengye, et al.
Published: (2024)

Bits Leaked per Query: Information-Theoretic Bounds on Adversarial Attacks against LLMs
by: Kaneko, Masahiro, et al.
Published: (2025)

Evaluating Precise Geolocation Inference Capabilities of Vision Language Models
by: Jay, Neel, et al.
Published: (2025)

Building a Robust Risk-Based Access Control System to Combat Ransomware's Capability to Encrypt
by: Begovic, Kenan, et al.
Published: (2026)

Certified Robust Accuracy of Neural Networks Are Bounded due to Bayes Errors
by: Zhang, Ruihan, et al.
Published: (2024)

Locket: Robust Feature-Locking Technique for Language Models
by: He, Lipeng, et al.
Published: (2025)

Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets
by: Zhang, Yechao, et al.
Published: (2025)

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
by: Chao, Patrick, et al.
Published: (2024)

Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering
by: Rashid, Md Rafi Ur, et al.
Published: (2023)

2-in-1 Accelerator: Enabling Random Precision Switch for Winning Both Adversarial Robustness and Efficiency
by: Fu, Yonggan, et al.
Published: (2021)

Information Leakage from Embedding in Large Language Models
by: Wan, Zhipeng, et al.
Published: (2024)

Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks
by: Noorbakhsh, Sayedeh Leila, et al.
Published: (2024)

Adaptive and Robust Data Poisoning Detection and Sanitization in Wearable IoT Systems using Large Language Models
by: Mithsara, W. K. M, et al.
Published: (2025)

MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Models
by: Yamabe, Shojiro, et al.
Published: (2024)

Directional Embedding Smoothing for Robust Vision Language Models
by: Wang, Ye, et al.
Published: (2026)

Learning Robust and Privacy-Preserving Representations via Information Theory
by: Zhang, Binghui, et al.
Published: (2024)

MM-FusionNet: Context-Aware Dynamic Fusion for Multi-modal Fake News Detection with Large Vision-Language Models
by: He, Junhao, et al.
Published: (2025)

Game-Theoretic Unlearnable Example Generator
by: Liu, Shuang, et al.
Published: (2024)

Towards Scalable and Robust Model Versioning
by: Ding, Wenxin, et al.
Published: (2024)

Differentially Private Domain Adaptation with Theoretical Guarantees
by: Bassily, Raef, et al.
Published: (2023)

Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data
by: Zhou, Yvonne, et al.
Published: (2024)

Jailbroken Frontier Models Retain Their Capabilities
by: Zhu, Daniel, et al.
Published: (2026)

Tighter Risk Bounds for Mixtures of Experts
by: Akretche, Wissam, et al.
Published: (2024)

Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities
by: Anurin, Andrey, et al.
Published: (2024)

Robust Distortion-free Watermarks for Language Models
by: Kuditipudi, Rohith, et al.
Published: (2023)

Goal-oriented Backdoor Attack against Vision-Language-Action Models via Physical Objects
by: Zhou, Zirun, et al.
Published: (2025)

PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts
by: Zhu, Kaijie, et al.
Published: (2023)

Low-Cost Hard-Label Adversarial Attack with Theoretical Foundations
by: Liu, Jun, et al.
Published: (2026)

Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack
by: Meng, Nicole, et al.
Published: (2024)

Enabling Adversarial Robustness in AI Models through Kubeflow MLOps
by: Bouras, Stavros, et al.
Published: (2026)

Robustness of Selected Learning Models under Label-Flipping Attack
by: Bhargava, Sarvagya, et al.
Published: (2025)

Position: Certified Robustness Does Not (Yet) Imply Model Security
by: Cullen, Andrew C., et al.
Published: (2025)

Augmenting Parameter-Efficient Pre-trained Language Models with Large Language Models
by: Anand, Saurabh, et al.
Published: (2026)

Model-Guardian: Protecting against Data-Free Model Stealing Using Gradient Representations and Deceptive Predictions
by: Yang, Yunfei, et al.
Published: (2025)

Privacy Amplification for the Gaussian Mechanism via Bounded Support
by: Hu, Shengyuan, et al.
Published: (2024)

FreeMOCA: Memory-Free Continual Learning for Malicious Code Analysis
by: Asadi, Zahra, et al.
Published: (2026)