paper-with-me

Papers

PICO: Secure Transformers via Robust Prompt Isolation and Cybersecurity Oversight

2025-04-26 · Ben Goertzel, Paulos Yibelo

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.

📄 PDF Abstract BibTeX arXiv:2504.21029

Code (0)

등록된 구현이 없습니다.

Tasks

Mixture-of-ExpertsPICOResponse Generation

Similar Papers 제목 키워드 기반

PicoDomain: A Compact High-Fidelity Cybersecurity Dataset

2020-08-20 · Craig Laprade, Benjamin Bowman, H. Howie Huang

Analysis of cyber relevant data has become an area of increasing focus. As larger percentages of businesses and governments begin to understand the implications of cyberattacks, the impetus for better cybersecurity solut…

Vocal Bursts Intensity Prediction

SecureBERT: A Domain-Specific Language Model for Cybersecurity

2022-04-06 · Ehsan Aghaei, Xi Niu, Waseem Shadid, Ehab Al-Shaer

Natural Language Processing (NLP) has recently gained wide attention in cybersecurity, particularly in Cyber Threat Intelligence (CTI) and cyber automation. Increased connection and automation have revolutionized the wor…

Language ModelingLanguage ModellingMasked Language Modelingmodel+1

SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code via Prompt Optimization

2026-05-08 · Houjun Liu, Lisa Einstein, John Yang, Joachim Baumann 외 arxiv

LLM coding agents now generate code at an unprecedented scale, yet LLM-generated code introduces cybersecurity vulnerabilities into codebases without human involvement. Even when frontier models are explicitly asked to w…

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges

2025-06-01 · Lajos Muzsai, David Imolai, András Lukács

Large Language Models (LLMs) still struggle with the structured reasoning and tool-assisted computation needed for problem solving in cybersecurity applications. In this work, we introduce "random-crypto", a cryptographi…

SecureCAI: Injection-Resilient LLM Assistants for Cybersecurity Operations

2026-01-12 · Mohammed Himayath Ali, Mohammed Aqib Abdullah, Mohammed Mudassir Uddin, Shahnawaz Alam arxiv

Large Language Models have emerged as transformative tools for Security Operations Centers, enabling automated log analysis, phishing triage, and malware explanation; however, deployment in adversarial cybersecurity envi…