LTBD: Learnable Trust-Boundary Delimiters for Prompt Injection Defense
To address this, we introduce Learnable Trust-Boundary Delimiters (LTBD), a lightweight defense that explicitly encodes trust boundaries in the input while keeping the LLM parameters unchanged.
Key points
- Large language models (LLMs) perform remarkably well on complex tasks, yet remain highly vulnerable to prompt injection attacks, where malicious instructions embedded in external data can override user intent.
- Existing defenses remain limited by model fine-tuning requirements, vulnerability to adaptive attacks, or reliance on brittle handcrafted prompts.
- LTBD uses a small number of learnable delimiters to distinguish trusted user instructions from untrusted external data, enabling the model to better respect the intended trust hierarchy.
- Experimental results show that LTBD substantially outperforms inference-time defenses and performs competitively with training-based approaches, while preserving benign-task utility and introducing negligible inference overhead.
Sources (1)
- [1]LTBD: Learnable Trust-Boundary Delimiters for Prompt Injection DefensearXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 10:13 AM
To address this, we introduce Learnable Trust-Boundary Delimiters (LTBD), a lightweight defense that explicitly encodes trust boundaries in the input while keeping the LLM parameters unchanged.
Large language models (LLMs) perform remarkably well on complex tasks, yet remain highly vulnerable to prompt injection attacks, where malicious instructions embedded in external data can override user intent.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 8, 2026Beyond Imitation: A Framework and Benchmark for LLM-Assisted Peer Review
- Oct 8, 2026SuperNav: An Agentic Navigation System for Any Task in Any Scene
- Oct 8, 2026VibeEdit: Image Editing with Canvas Instructions
- Oct 8, 2026SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models
- Oct 7, 2026Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning
- Oct 7, 2026Q-Learning with Scalar Adjoint Matching