PICO: Secure Transformers via Robust Prompt Isolation and Cybersecurity Oversight
On the map: LLM safety and security → Prompt injection and agent security
Abstract (arXiv)
We propose a robust transformer architecture designed to prevent prompt injection attacks and ensure secure, reliable response generation. Our PICO (Prompt Isolation and Cybersecurity Oversight) framework structurally separates trusted system instructions from untrusted user inputs through dual channels that are processed independently and merged only by a controlled, gated fusion mechanism. In addition, we integrate a specialized Security Expert Agent within a Mixture-of-Experts (MoE) framework and incorporate a Cybersecurity Knowledge Graph (CKG) to supply domain-specific reasoning. Our training design further ensures that the system prompt branch remains immutable while the rest of the network learns to handle adversarial inputs safely. This PICO framework is presented via a general mathematical formulation, then elaborated in terms of the specifics of transformer architecture, and fleshed out via hypothetical case studies including Policy Puppetry attacks. While the most effective implementation may involve training transformers in a PICO-based way from scratch, we also present a cost-effective fine-tuning approach.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Prompt injection and agent security, one of 12 directions in LLM safety and security. Builds on 3 of its 6 references that are in the map. First posted on arXiv 26 Apr 2025.
Builds on
3 of 6 references.
Closest ancestors · 1
Same direction, newest first
Other references · 2
- 2017Attention Is All You Needcited by 60,361
- 2022A review of knowledge graph application scenarios in cyber securitycited by 6
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Pruning and Malicious Injection: A Retraining-Free Backdoor Attack on Transformer Models
- 2026SecureCAI: Injection-Resilient LLM Assistants for Cybersecurity Operations
- 2024Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits
- 2026Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat Mitigation
- 2026DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers
- 2026SEAL: Reinforcing Global Safety in Mixture-of-Experts through Shared Expert ALignment
- 2026GrayShield: Bit-Level Sanitization for Transformer Model Supply-Chain Security
- 2026Policy-Masked Private Experts: Auditable and Reversible Capability Access Control in Sparse MoE Models