When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models

arXiv:2605.11612 · cs.CL, cs.AI · Submitted 2026-05-12 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-05-12

Updated: 2026-08-26

Code: https://github.com/tatsu-lab/stanford

Terminology

• Fine-Tuning — 22× in this paper · explained in 5 episodes
• Cosine Similarity — 5× in this paper · explained in 3 episodes
• Instruction Tuning — 5× in this paper · explained in 2 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Attack Success Rate — 4× in this paper
• Accuracy — 3× in this paper · explained in 1 episode
• Consistency — 3× in this paper · explained in 3 episodes
• Distillation — 3× in this paper · explained in 2 episodes
• Fidelity — 3× in this paper · explained in 2 episodes
• Regularization — 3× in this paper · explained in 3 episodes
• Semantic Similarity — 3× in this paper · explained in 2 episodes
• Transferability — 3× in this paper · explained in 4 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Average Treatment Effect — 2× in this paper
• Data Augmentation — 2× in this paper · explained in 7 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• F1 Score — 2× in this paper · explained in 3 episodes
• Knowledge Distillation — 2× in this paper · explained in 11 episodes
• Latent Representation — 2× in this paper · explained in 2 episodes
• Latent Space — 2× in this paper · explained in 7 episodes
• Pruning — 2× in this paper · explained in 4 episodes
• Virtual Prompt Injection — 2× in this paper
• Benchmark — 1× in this paper · explained in 2 episodes
• Catastrophic Forgetting — 1× in this paper · explained in 5 episodes
• Clean Accuracy — 1× in this paper
• Clean Supervised Fine-tuning — 1× in this paper
• Clustering — 1× in this paper · explained in 2 episodes
• Composite Backdoor Attack — 1× in this paper
• Cooperation — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Regret — 1× in this paper · explained in 3 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Mistral 7B
• Qwen2.5 Technical Report
• ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools
• Qwen3 Technical Report

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