Dependable Artificial Intelligence with Reliability and Security (DAIReS): A Unified Syndrome Decoding Approach for Hallucination and Backdoor Trigger Detection

2026-02-06

AI Summary

This work addresses critical security and reliability threats in machine learning models—namely, backdoor data poisoning and hallucinations in large language models—that can lead to untrustworthy outputs. The authors propose a unified framework based on syndrome decoding to simultaneously detect backdoored training samples and hallucinated content within the sentence embedding space. This approach represents the first application of syndrome decoding to both security and reliability challenges, leveraging meta-explanatory task modeling and an anomaly discrimination mechanism to enable generalizable detection across distinct problem settings. Experimental results demonstrate that the method effectively distinguishes poisoned from clean data and accurately identifies hallucinations through reflexive meta-explanations, thereby significantly enhancing the trustworthiness of AI systems.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Natural Language Processing: Safety and Robustness
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Large language models for search
• Security and Privacy: Security and privacy of machine learning and AI applications

Abstract

Machine Learning (ML) models, including Large Language Models (LLMs), are characterized by a range of system-level attributes such as security and reliability. Recent studies have demonstrated that ML models are vulnerable to multiple forms of security violations, among which backdoor data-poisoning attacks represent a particularly insidious threat, enabling unauthorized model behavior and systematic misclassification. In parallel, deficiencies in model reliability can manifest as hallucinations in LLMs, leading to unpredictable outputs and substantial risks for end users. In this work on Dependable Artificial Intelligence with Reliability and Security (DAIReS), we propose a novel unified approach based on Syndrome Decoding for the detection of both security and reliability violations in learning-based systems. Specifically, we adapt the syndrome decoding approach to the NLP sentence-embedding space, enabling the discrimination of poisoned and non-poisoned samples within ML training datasets. Additionally, the same methodology can effectively detect hallucinated content due to self referential meta explanation tasks in LLMs.

Problem

• backdoor attack
• hallucination
• reliability
• security
• data poisoning

Innovation

• Syndrome Decoding
• Backdoor Detection
• Hallucination Detection
• Dependable AI
• Sentence Embedding