Image de couverture de livre

Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	ElZemity, Adel, Arief, Budi, Li, Shujun
Format:	Preprint
Publié:	2025
Sujets:	Cryptography and Security Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

CyberLLMInstruct: A Pseudo-malicious Dataset Revealing Safety-performance Trade-offs in Cyber Security LLM Fine-tuning
par: ElZemity, Adel, et autres
Publié: (2025)

Privacy Threats and Countermeasures in Federated Learning for Internet of Things: A Systematic Review
par: ElZemity, Adel, et autres
Publié: (2024)

APIOT: Autonomous Vulnerability Management Across Bare-Metal Industrial OT Networks
par: ElZemity, Adel, et autres
Publié: (2026)

Agentic Knowledge Distillation: Autonomous Training of Small Language Models for SMS Threat Detection
par: ElZemity, Adel, et autres
Publié: (2026)

Benchmarking Safety Risks of Knowledge-Intensive Reasoning under Malicious Knowledge Editing
par: Mao, Qinghua, et autres
Publié: (2026)

Differentiation-Based Extraction of Proprietary Data from Fine-Tuned LLMs
par: Li, Zongjie, et autres
Publié: (2025)

A Systematic Evaluation of Parameter-Efficient Fine-Tuning Methods for the Security of Code LLMs
par: Lee, Kiho, et autres
Publié: (2025)

Defending MoE LLMs against Harmful Fine-Tuning via Safety Routing Alignment
par: Kim, Jaehan, et autres
Publié: (2025)

Operationalising Cyber Risk Management Using AI: Connecting Cyber Incidents to MITRE ATT&CK Techniques, Security Controls, and Metrics
par: Sherif, Emad, et autres
Publié: (2026)

The Authorization-Execution Gap Is a Major Safety and Security Problem in Open-World Agents
par: Wu, Baoyuan, et autres
Publié: (2026)

SDD: Self-Degraded Defense against Malicious Fine-tuning
par: Chen, Zixuan, et autres
Publié: (2025)

Fine-Tuning, Quantization, and LLMs: Navigating Unintended Outcomes
par: Kumar, Divyanshu, et autres
Publié: (2024)

AI Risk Management Should Incorporate Both Safety and Security
par: Qi, Xiangyu, et autres
Publié: (2024)

Persistent Backdoor Attacks under Continual Fine-Tuning of LLMs
par: Cui, Jing, et autres
Publié: (2025)

From Incomplete Architecture to Quantified Risk: Multimodal LLM-Driven Security Assessment for Cyber-Physical Systems
par: Huang, Shaofei, et autres
Publié: (2026)

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets
par: Lu, Ning, et autres
Publié: (2025)

Security Document Classification with a Fine-Tuned Local Large Language Model: Benchmark Data and an Open-Source System
par: Dobrovolskyi, Ivan
Publié: (2026)

DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning
par: Zhang, Junbo, et autres
Publié: (2026)

HonestCyberEval: An AI Cyber Risk Benchmark for Automated Software Exploitation
par: Ristea, Dan, et autres
Publié: (2024)

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
par: Hossain, Saad, et autres
Publié: (2026)

SecureReg: Combining NLP and MLP for Enhanced Detection of Malicious Domain Name Registrations
par: Çolhak, Furkan, et autres
Publié: (2024)

BugWhisperer: Fine-Tuning LLMs for SoC Hardware Vulnerability Detection
par: Tarek, Shams, et autres
Publié: (2025)

Emerging Cyber Attack Risks of Medical AI Agents
par: Qiu, Jianing, et autres
Publié: (2025)

Self-Mined Hardness for Safety Fine-Tuning
par: Gupta, Prakhar, et autres
Publié: (2026)

Large Language Models for Cyber Security: A Systematic Literature Review
par: Xu, Hanxiang, et autres
Publié: (2024)

Scam Shield: Multi-Model Voting and Fine-Tuned LLMs Against Adversarial Attacks
par: Chang, Chen-Wei, et autres
Publié: (2025)

CyberSentinel: An Emergent Threat Detection System for AI Security
par: Tallam, Krti
Publié: (2025)

Agentic AI for Cyber Resilience: A New Security Paradigm and Its System-Theoretic Foundations
par: Li, Tao, et autres
Publié: (2025)

CurricuLLM: Designing Personalized and Workforce-Aligned Cybersecurity Curricula Using Fine-Tuned LLMs
par: Nijdam, Arthur, et autres
Publié: (2026)

SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data Selection
par: Chen, Shuhao, et autres
Publié: (2026)

Defensive Refusal Bias: How Safety Alignment Fails Cyber Defenders
par: Campbell, David, et autres
Publié: (2026)

BARTPredict: Empowering IoT Security with LLM-Driven Cyber Threat Prediction
par: Diaf, Alaeddine, et autres
Publié: (2025)

CyberCertBench: Evaluating LLMs in Cybersecurity Certification Knowledge
par: Keppler, Gustav, et autres
Publié: (2026)

Contextualized AI for Cyber Defense: An Automated Survey using LLMs
par: Haryanto, Christoforus Yoga, et autres
Publié: (2024)

CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence
par: Alam, Md Tanvirul, et autres
Publié: (2024)

VeriLoRA: Fine-Tuning Large Language Models with Verifiable Security via Zero-Knowledge Proofs
par: Liao, Guofu, et autres
Publié: (2025)

Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique
par: Li, Yanming, et autres
Publié: (2025)

Comparative Analysis of Black-Box and White-Box Machine Learning Model in Phishing Detection
par: Fajar, Abdullah, et autres
Publié: (2024)

Enhancing Phishing Detection through Feature Importance Analysis and Explainable AI: A Comparative Study of CatBoost, XGBoost, and EBM Models
par: Fajar, Abdullah, et autres
Publié: (2024)

LADFA: A Framework of Using Large Language Models and Retrieval-Augmented Generation for Personal Data Flow Analysis in Privacy Policies
par: Yuan, Haiyue, et autres
Publié: (2026)