The Customer Never Sees the Goal: Measuring and Detecting Vulnerability-Targeted Manipulation in LLM Assistants
cs.CR, cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Phi-4 Technical Report
- Evaluating Language Models for Harmful Manipulation
- Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
- A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI
- Gemini: A Family of Highly Capable Multimodal Models
- Ministral 3
- GPT-4 Technical Report
- Qwen2.5 Technical Report
- Large Language Models can Strategically Deceive their Users when Put Under Pressure
- The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
- Qwen3 Technical Report
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data