SAFESHIELD: A Decision-Organization Framework for Deployment-Time Safety of Small Language Models

Deployment-time safety of language models is commonly implemented through runtime guardrails such as input moderation, routing, retrieval verification, and output filtering. Existing deployment frameworks provide increasingly capable mechanisms for these functions, but offer limited guidance on h...

Merging Cyber Threat Intelligence through Retrieval-Augmented Generation and Small Language Models for Rich Threat Representation

Modern cybersecurity operations rely on CTI collected from heterogeneous sources, including semi-structured threat representations, IoCs, and narrative technical reports. However, these artifacts are often insufficient in isolation to reconstruct how an attack unfolds, under which conditions each...

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA

Large Language Models LLMs are increasingly fine-tuned for critical-domain Question-Answering QA, yet choosing which small model to adapt, before paying the cost of adaptation, remains difficult. Fine-tuning can improve domain alignment, but it may also erode prior knowledge, weaken...

Decomposing Memorization Reduction in Privacy-Preserving Fine-Tuning of SLMs for CSIRTs

CSIRTs increasingly fine tune language models on vulnerability scan records, but these records expose internal network topology and create privacy risks under regulations such as GDPR and LGPD. We present the first empirical study of how DP SGD and HMAC pseudonymization interact when fine tuning...

Your 100 Billion Parameter Behemoth is a Liability

The "bigger is better" era of AI is hitting a wall. We are in an LLM bubble, characterized by ruinous inference costs and diminishing returns. The future belongs to Agentic AI powered by specialized Small Language Models SLMs. Think of it as a shift from hiring a single expensive genius to runnin...

Towards Small Language Models for Security Query Generation in SOC Workflows

Analysts in Security Operations Centers routinely query massive telemetry streams using Kusto Query Language KQL. Writing correct KQL requires specialized expertise, and this dependency creates a bottleneck as security teams scale. This paper investigates whether Small Language Models SLMs can...

Small Language Models for Phishing Website Detection: Cost, Performance, and Privacy Trade-Offs

Phishing websites pose a major cybersecurity threat, exploiting unsuspecting users and causing significant financial and organisational harm. Traditional machine learning approaches for phishing detection often require extensive feature engineering, continuous retraining, and costly infrastructur...

EASE: Practical and Efficient Safety Alignment for Small Language Models

Small language models SLMs are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust protection, particularly against adversarial jailbreaks. While...

Toward Cybersecurity-Expert Small Language Models

Large language models LLMs are transforming everyday applications, yet deployment in cybersecurity lags due to a lack of high-quality, domain-specific models and training datasets. To address this gap, we present CyberPal 2.0, a family of cybersecurity-expert small language models SLMs ranging fr...

LiteLMGuard: Seamless and Lightweight On-Device Prompt Filtering for Safeguarding Small Language Models against Quantization-Induced Risks and Vulnerabilities

The growing adoption of Large Language Models LLMs has influenced the development of their lighter counterparts-Small Language Models SLMs-to enable on-device deployment across smartphones and edge devices. These SLMs offer enhanced privacy, reduced latency, server-free functionality, and improve...

Case Study: Fine-Tuning Small Language Models for Accurate and Private CWE Detection in Python Code

Large Language Models LLMs have demonstrated significant capabilities in understanding and analyzing code for security vulnerabilities, such as Common Weakness Enumerations CWEs. However, their reliance on cloud infrastructure and substantial computational requirements pose challenges for analyzi...