No article text was recorded for this version.
adversarial vulnerability (adversarial vulnerability of VLMs)
Version 2 of 2208 papers272 conceptsfrozen 2026-10-04
Papers in this version
- Blog: An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models
- Blog: Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques
- Blog: FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models
- Blog: Improving Adversarial Robustness in Vision-Language Models with Architecture and Prompt Design
- Blog: How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs
- Blog: Adversarial Robustness for Visual Grounding of Multimodal Large Language Models
- Blog: Enhancing Adversarial Robustness of Vision-Language Models through Low-Rank Adaptation
- Blog: How Many Are in This Image A Safety Evaluation Benchmark for Vision LLMs
- Blog: On the Adversarial Robustness of Multi-Modal Foundation Models
- Blog: On the Feasibility of Poisoning Text-to-Image AI Models via Adversarial Mislabeling
- Blog: Fast Certification of Vision-Language Models Using Incremental Randomized Smoothing
- Blog: GLEAM: Enhanced Transferable Adversarial Attacks for Vision-Language Pre-training Models via Global-Local Transformations
- Blog: InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models
- Blog: Web Artifact Attacks Disrupt Vision Language Models
- Blog: R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning
- Blog: Don’t Buy it! Reassessing the Ad Understanding Abilities of Contrastive Multimodal Models
- Blog: Multimodal Adversarial Defense for Vision-Language Models by Leveraging One-To-Many Relationships
- Blog: VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a Service
- Blog: Semantic-aware Adversarial Fine-tuning for CLIP
- Blog: Automatically Generating Visual Hallucination Test Cases for Multimodal Large Language Models
- Blog: DASH: Detection and Assessment of Systematic Hallucinations of VLMs
- Blog: UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images
- Blog: AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Adversarial Visual-Instructions
- Blog: One Prompt Word is Enough to Boost Adversarial Robustness for Pre-Trained Vision-Language Models
- Blog: Investigating Robustness of Open-Vocabulary Foundation Object Detectors under Distribution Shifts
- Blog: QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models
- Blog: TIMA: Text-Image Mutual Awareness for Balancing Zero-Shot Adversarial Robustness and Generalization Ability
- Blog: Hydra: An Agentic Reasoning Approach for Enhancing Adversarial Robustness and Mitigating Hallucinations in Vision-Language Models
- Blog: Detecting and Evaluating Medical Hallucinations in Large Vision Language Models
- Blog: ATAC: Augmentation-Based Test-Time Adversarial Correction for CLIP
- Blog: QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models
- Blog: Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
- Blog: X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
- Blog: Few-Shot Adversarial Prompt Learning on Vision-Language Models
- Blog: Adversarial Attacks on Robotic Vision Language Action Models
- Blog: Transferable Visual Adversarial Attacks for Proprietary Multimodal Large Language Models
- Blog: ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents
- Blog: An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models
- Blog: Self-interpreting Adversarial Images
- Blog: Laundering AI Authority with Adversarial Examples
- Blog: Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks
- Blog: Coordinated Robustness Evaluation Framework for Vision Language Models
- Blog: Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models
- Blog: Endowing Visual Reprogramming with Adversarial Robustness
- Blog: MirrorCheck: Efficient Adversarial Defense for Vision-Language Models
- Blog: On the Robustness of GUI Grounding Models Against Image Attacks
- Blog: Attacking Vision-Language Computer Agents via Pop-ups
- Blog: NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models
- Blog: MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMs
- Blog: Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks
- Blog: Towards Fine-Grained Robustness: Attention-Guided Test-Time Prompt Tuning for Vision-Language Models
- Blog: Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models
- Blog: On Evaluating Adversarial Robustness of Large Vision-Language Models
- Blog: FedAPT: Federated Adversarial Prompt Tuning for Vision-Language Models
- Blog: MMT-ARD: Multimodal Multi-Teacher Adversarial Distillation for Robust Vision-Language Models
- Blog: Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness
- Blog: Localize and Neutralize: Gradient-Guided Token Suppression Against Visual Prompt Injection Attack
- Blog: AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization
- Blog: Partially Recentralization Softmax Loss for Vision-Language Models Robustness
- Blog: Few Tokens Matter: Entropy Guided Attacks on Vision-Language Models
Showing 60 of 208 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_adversarial_vulnerability_adversarial_vu_0481e866,
title = {adversarial vulnerability (adversarial vulnerability of VLMs)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/adversarial-vulnerability-adversarial-vulnerability-of-vlms/rdr_0481e866b673424cae106186dff3e81d},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_adversarial_vulnerability_adversarial_vu_0481e866_v2,
title = {adversarial vulnerability (adversarial vulnerability of VLMs)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/adversarial-vulnerability-adversarial-vulnerability-of-vlms/rdr_0481e866b673424cae106186dff3e81d/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}