The list of accepted papers for NLPAICS 2026 are:

• Grieve-JA: A Psycholinguistic Dictionary for Grievance-Fuelled Language in Japanese
• How Well Do Commodity Text-to-Speech Systems Evade Acoustic Perturbation Detection? A Multi-Engine Evaluation Across 21 Languages
• Prompt Injection in Large Language Models: A Linguistic Analysis of Manipulation Strategies
• Large-Scale Multilingual SMS Fraud Detection For Telecom Networks
• Partner Attribution Bias in LLM-Assisted Export Control Screening
• FACEGUARD: A Dataset for Detecting NLP-Driven Facial Image Manipulation
• An Interpretable Approach to Bias Detection in News Headlines Using NLP and Color-Coded Visualization Techniques
• Exploring Cross-Lingual Transfer in Transformer-Based Fraud Detection Models
• Contrastive Representation Learning for Transformer-Based Phishing Email Detection
• Pragmatic Profiling for Disinformation Detection: An Exploratory Analysis of Stylistic Features in Spanish News
• Privacy VITA: a new multilingual and multimodal annotated video corpus to evaluate anonymization systems
• Fraud detection model: A discriminative language model for fraud detection and prioritization in Financial communications
• How Vulnerable Are the Most Popular MCP Servers? An Empirical Study of Third-Party Dependency Risks
• CEFR-Controlled Readability in Arabic Prompts: Implications for Jailbreak Behavior in Large Language Models
• NLP-Assisted Threat Intelligence for the Colombian Public Sector: Characterizing Malware Incidents from Open-Source Textual Reporting
• Exploring the Manifestation of Schwartz’s Basic Human Values in Large Language Models
•  From Decision Tree to Detection Pipeline: Formalizing van Dijk’s Socio-Cognitive Framework for Automated Anti-Language Identification in RICO Transcripts
• Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study
• When Privacy Helps: Pseudonymisation as a Strategy for Improved Cyber Incident Classification
• Fine-Tuning Small Language Models for Cybersecurity: Data Ordering, Knowledge Distillation, and the Educator Effect
• LLM-based Defense Against Adversarial Abstracts in ML/AI Conference Reviewer Assignments
• Command-Line Obfuscation Detection in Real-World Telemetry under Extreme Class Imbalance
• Transformer-Assisted LLM-Based Source Code Summarisation: to Enable More Secure Software Development
• Semantic Clustering of Obfuscated Command-Line Detections for Alert Reduction
• Does Hate Transfer? Cross-Lingual Generalisation of Offensive Content Detection Across Indic Languages
• A Neuro-Cyber Exploitation and Reconnaissance Taxonomy (NeuroCERT) for Human-Centric Cybersecurity
• Bloc-Conditional Event States: Measuring Cross-Coverage Divergence for Threat-Intelligence Analysis
• From Detection to Attribution: Forensic Linguistics and Adversarial Red Teaming as Complementary Responses to LLM Misuse
• LLMs in the Enterprise: A Systematic Review of Security Architectures for RAG-Augmented Chatbots
• Code Without Context: Can We Trust LLMs to Test Software from Informal Descriptions?
• The Human Attack Surface: Detecting Psychological Vulnerabilities to Cyber Threats using AI and Social Media
• OBSIDIAN: An OSINT-Driven NLP Framework for Detecting Cyber-Physical Threats in Arabic Social Media
• Judging the LLM Judges: A Human-Centric Validation of LLM-Generated Training Data for Software Retrieval
• CSULoRA: Closest Safe Update Low-Rank Adaptation