ChartAttack: Testing the Vulnerability of LLMs to Malicious Prompting in Chart Generation

arXiv:2601.12983 · cs.CL · Submitted 2026-01-19 · Read on arXiv

cs.CL

Submitted: 2026-01-19

Updated: 2026-09-01

Code: https://github.com/insait-institute/chartAttack

Terminology

• Accuracy — 48× in this paper · explained in 1 episode
• Robustness — 14× in this paper · explained in 5 episodes
• Benchmark — 6× in this paper · explained in 2 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Benchmarking — 3× in this paper · explained in 4 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Quantization — 3× in this paper · explained in 12 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• In-Context Learning — 2× in this paper · explained in 4 episodes
• Instruction Tuning — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Parameter-Efficient Fine-Tuning — 1× in this paper · explained in 2 episodes
• Structured Reasoning — 1× in this paper · explained in 3 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes

Sources

• Automated Visualization Makeovers with LLMs
• Qwen2.5-VL Technical Report
• DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
• Efficient Natural Language Response Suggestion for Smart Reply
• CHARTOM: A Visual Theory-of-Mind Benchmark for LLMs on Misleading Charts
• Qwen2.5-Coder Technical Report
• The Perils of Chart Deception: How Misleading Visualizations Affect Vision-Language Models
• Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
• Ovis2.5 Technical Report
• Kimi-VL Technical Report
• Qwen3 Technical Report
• Protecting multimodal large language models against misleading visualizations
• Is this chart lying to me? Automating the detection of misleading visualizations
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• From Deception to Detection: The Dual Roles of Large Language Models in Fake News
• HuggingFace's Transformers: State-of-the-art Natural Language Processing
• GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• HumanEval-V: Benchmarking High-Level Visual Reasoning with Complex Diagrams in Coding Tasks
• InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering