Research map / Adversarial robustness and security / Attacks on text and graphs

RobustGenBench: A Benchmark for Robust Generalization to Adversarial and Common Perturbations, with Applications to Vision and Vision-Enabled Large Language Models

NeurIPS 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Vision-language model robustness

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces RobustGenBench, a standardized benchmark of six classification datasets for evaluating robust generalization to adversarial and common perturbations across robust fine-tuned vision models and vision-enabled LLMs.

Problem

Robust generalization across diverse perturbation settings is poorly understood for modern classifiers, including robust fine-tuning from pretrained backbones and zero-shot classification with vision-enabled LLMs.

Approach

A unified standardized benchmark with reproducible evaluation splits covering both adversarial and common perturbations, applied to robust fine-tuned vision models and zero-shot Ve-LLMs.

Experimental setup

Datasets: six classification datasets

Benchmarks: RobustGenBench

Metrics: robust accuracy

Closest papers by meaning

• R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning (CVPR 2025 · similarity 0.89)
• VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language Models (ICML 2026 · similarity 0.89)
• Improving Zero-Shot Adversarial Robustness in Vision-Language Models by Closed-form Alignment of Adversarial Path Simplices (ICML 2025 · similarity 0.88)
• One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models (CVPR 2024 · similarity 0.88)
• Scaling Test-Time Robustness of Vision-Language Models via Self-Critical Inference Framework (CVPR 2026 · similarity 0.88)
• LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders (NeurIPS 2025 · similarity 0.88)