The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models
cs.CR, cs.LG
Submitted: 2026-10-06
Updated: 2026-10-06
Code: https://github.com/Yibo124/answer-side-backdoor
Terminology
Sources
- Constitutional AI: Harmlessness from AI Feedback
- Enhancing Chat Language Models by Scaling High-quality Instructional Conversations
- Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation
- Mistral 7B
- Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs
- Turn-Based Structural Triggers: Structure-Conditioned Backdoors in Multi-Turn LLMs
- GPT-4o System Card
- BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage
- Gemma: Open Models Based on Gemini Research and Technology
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs
- A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs