Cover Image

The H-Elena Trojan Virus to Infect Model Weights: A Wake-Up Call on the Security Risks of Malicious Fine-Tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tejedor, Virilo, Zuheros, Cristina, Peláez-González, Carlos, Herrera-Poyatos, David, Herrera-Poyatos, Andrés, Herrera, Francisco
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Domain-Based Taxonomy of Jailbreak Vulnerabilities in Large Language Models
by: Peláez-González, Carlos, et al.
Published: (2025)

An overview of model uncertainty and variability in LLM-based sentiment analysis. Challenges, mitigation strategies and the role of explainability
by: Herrera-Poyatos, David, et al.
Published: (2025)

Triadic Fusion of Cognitive, Functional, and Causal Dimensions for Explainable LLMs: The TAXAL Framework
by: Herrera-Poyatos, David, et al.
Published: (2025)

Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data
by: ElZemity, Adel, et al.
Published: (2025)

Large language models for crowd decision making based on prompt design strategies using ChatGPT: models, analysis and challenges
by: Herrera-Poyatos, David, et al.
Published: (2024)

Infecting Generative AI With Viruses
by: Noever, David, et al.
Published: (2025)

TrojanPraise: Jailbreak LLMs via Benign Fine-Tuning
by: Xie, Zhixin, et al.
Published: (2026)

Neural Trojans
by: Liu, Yuntao, et al.
Published: (2017)

TrojanLoC: LLM-based Framework for RTL Trojan Localization
by: Xiao, Weihua, et al.
Published: (2025)

WAFBOOSTER: Automatic Boosting of WAF Security Against Mutated Malicious Payloads
by: Wu, Cong, et al.
Published: (2025)

FLEX: FLEXible Federated Learning Framework
by: Herrera, Francisco, et al.
Published: (2024)

Hackphyr: A Local Fine-Tuned LLM Agent for Network Security Environments
by: Rigaki, Maria, et al.
Published: (2024)

MaliGNNoma: GNN-Based Malicious Circuit Classifier for Secure Cloud FPGAs
by: Alrahis, Lilas, et al.
Published: (2024)

Efficient and High-Accuracy Private CNN Inference with Helper-Assisted Malicious Security
by: Wang, Kaiwen, et al.
Published: (2025)

HeisenTrojans: They Are Not There Until They Are Triggered
by: Mavurapu, Akshita Reddy, et al.
Published: (2023)

Camel: Communication-Efficient and Maliciously Secure Federated Learning in the Shuffle Model of Differential Privacy
by: Xu, Shuangqing, et al.
Published: (2024)

SecureFed: A Two-Phase Framework for Detecting Malicious Clients in Federated Learning
by: Kavuri, Likhitha Annapurna, et al.
Published: (2025)

Detecting Malicious Entra OAuth Apps with LLM-Based Permission Risk Scoring
by: Mahara, Ashim
Published: (2025)

When FinTech Meets Privacy: Securing Financial LLMs with Differential Private Fine-Tuning
by: Zhu, Sichen, et al.
Published: (2025)

Securing WiFi Fingerprint-based Indoor Localization Systems from Malicious Access Points
by: Shifat, Fariha Tanjim, et al.
Published: (2025)

Unveiling Malicious Logic: Towards a Statement-Level Taxonomy and Dataset for Securing Python Packages
by: Ryan, Ahmed, et al.
Published: (2025)

Malicious GenAI Chrome Extensions: Unpacking Data Exfiltration and Malicious Behaviours
by: Seetharam, Shresta B., et al.
Published: (2025)

SDD: Self-Degraded Defense against Malicious Fine-tuning
by: Chen, Zixuan, et al.
Published: (2025)

Hardware Trojans in Quantum Circuits, Their Impacts, and Defense
by: Roy, Rupshali, et al.
Published: (2024)

Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks
by: Kuo, Kevin, et al.
Published: (2026)

Toward Automated Security Risk Detection in Large Software Using Call Graph Analysis
by: Pecka, Nicholas, et al.
Published: (2025)

FedMUP: Federated Learning driven Malicious User Prediction Model for Secure Data Distribution in Cloud Environments
by: Gupta, Kishu, et al.
Published: (2024)

An AI-Enabled Side Channel Power Analysis Based Hardware Trojan Detection Method for Securing the Integrated Circuits in Cyber-Physical Systems
by: Puspa, Sefatun-Noor, et al.
Published: (2024)

SCARF: Securing Chips with a Robust Framework against Fabrication-time Hardware Trojans
by: Eslami, Mohammad, et al.
Published: (2024)

Am I Infected? Lessons from Operating a Large-Scale IoT Security Diagnostic Service
by: Sasaki, Takayuki, et al.
Published: (2025)

The Philosopher's Stone: Trojaning Plugins of Large Language Models
by: Dong, Tian, et al.
Published: (2023)

Protecting Model Adaptation from Trojans in the Unlabeled Data
by: Sheng, Lijun, et al.
Published: (2024)

Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors
by: Sahabandu, Dinuka, et al.
Published: (2024)

TrojanWhisper: Evaluating Pre-trained LLMs to Detect and Localize Hardware Trojans
by: Faruque, Md Omar, et al.
Published: (2024)

TrojanDec: Data-free Detection of Trojan Inputs in Self-supervised Learning
by: Liu, Yupei, et al.
Published: (2025)

CallShield: Secure Caller Authentication over Real-Time Audio Channels
by: Rabh, Mouna, et al.
Published: (2026)

Quantifying Psychological Sophistication of Malicious Emails
by: Longtchi, Theodore, et al.
Published: (2024)

Enhancing Adversarial Transferability with Adversarial Weight Tuning
by: Chen, Jiahao, et al.
Published: (2024)

Risks When Sharing LoRA Fine-Tuned Diffusion Model Weights
by: Yao, Dixi
Published: (2024)

MAIDS: Malicious Agent Identification-based Data Security Model for Cloud Environments
by: Gupta, Kishu, et al.
Published: (2024)