It Takes Little to Rewrite Perception: Targeted Semantic Substitution in Vision-Language Models at epsilon at most 4/255

arXiv:2609.38298 · cs.CV, cs.LG · Submitted 2026-09-29 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-09-29

Updated: 2026-10-02

Terminology

• Robustness — 13× in this paper · explained in 5 episodes
• Adversarial Attacks — 11× in this paper · explained in 1 episode
• Alignment — 9× in this paper · explained in 1 episode
• Transferability — 6× in this paper · explained in 4 episodes
• Hallucination — 5× in this paper · explained in 3 episodes
• Generative AI — 4× in this paper · explained in 2 episodes
• Large Language Model — 4× in this paper
• Ablation — 3× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 2 episodes
• Adversarial Robustness — 3× in this paper · explained in 3 episodes
• Conference on Computer Vision and Pattern Recognition — 3× in this paper
• In International Conference on Learning Representations — 3× in this paper
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 2× in this paper · explained in 3 episodes
• Quantization — 2× in this paper · explained in 12 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Adversarial Examples — 1× in this paper · explained in 2 episodes
• Attack Success Rate — 1× in this paper
• Attack Success Rate (ASR) — 1× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Empirical Methods in Natural Language Processing — 1× in this paper
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• In European Conference on Computer Vision — 1× in this paper
• International Conference on Machine Learning — 1× in this paper
• Loss Function — 1× in this paper · explained in 2 episodes
• Optimal Transport — 1× in this paper · explained in 5 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes

Sources

• Qwen3-VL Technical Report
• Hallucination of Multimodal Large Language Models: A Survey
• Exploiting Vision Encoder Vulnerabilities for Universal Adversarial Perturbations on Large Vision-Language Models
• FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs
• CAVALRY-V: A Large-Scale Generator Framework for Adversarial Attacks on Video MLLMs

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models