Imagen de Portada

Swallowing the Poison Pills: Insights from Vulnerability Disparity Among LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yifeng, Peng, Zhizheng, Wu, Chen, Chen
Formato:	Preprint
Publicado:	2025
Materias:	Cryptography and Security Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights
por: Sheng, Ze, et al.
Publicado: (2025)

On The Dangers of Poisoned LLMs In Security Automation
por: Karlsen, Patrick, et al.
Publicado: (2025)

Persistent Pre-Training Poisoning of LLMs
por: Zhang, Yiming, et al.
Publicado: (2024)

Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks
por: Cotroneo, Domenico, et al.
Publicado: (2023)

PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning
por: Fu, Tingchen, et al.
Publicado: (2024)

Logic Meets Magic: LLMs Cracking Smart Contract Vulnerabilities
por: Xiao, ZeKe, et al.
Publicado: (2025)

Data Poisoning Vulnerabilities Across Healthcare AI Architectures: A Security Threat Analysis
por: Abtahi, Farhad, et al.
Publicado: (2025)

Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning
por: Yan, Shenao, et al.
Publicado: (2026)

P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs
por: Zhao, Shuai, et al.
Publicado: (2025)

From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs
por: Shen, Guangyu, et al.
Publicado: (2025)

Decoding Deception: Understanding Automatic Speech Recognition Vulnerabilities in Evasion and Poisoning Attacks
por: G, Aravindhan, et al.
Publicado: (2025)

LLMpatronous: Harnessing the Power of LLMs For Vulnerability Detection
por: Yarra, Rajesh
Publicado: (2025)

CSC: Turning the Adversary's Poison against Itself
por: Shi, Yuchen, et al.
Publicado: (2026)

Toward Polymorphic Backdoor against Semantic Communication via Intensity-Based Poisoning
por: Yang, Xiao, et al.
Publicado: (2026)

Poisoned Acoustics
por: Dahme, Harrison
Publicado: (2026)

Scaling Trends for Data Poisoning in LLMs
por: Bowen, Dillon, et al.
Publicado: (2024)

LoopTrap: Termination Poisoning Attacks on LLM Agents
por: Xu, Huiyu, et al.
Publicado: (2026)

Data Poisoning in Deep Learning: A Survey
por: Zhao, Pinlong, et al.
Publicado: (2025)

Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense
por: Zhang, Jiawen, et al.
Publicado: (2025)

Towards Compositional Generalization in LLMs for Smart Contract Security: A Case Study on Reentrancy Vulnerabilities
por: Zhou, Ying, et al.
Publicado: (2026)

On the Effectiveness of Instruction-Tuning Local LLMs for Identifying Software Vulnerabilities
por: Park, Sangryu, et al.
Publicado: (2025)

ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking
por: Wu, Yutao, et al.
Publicado: (2025)

Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents
por: Zou, Wei, et al.
Publicado: (2026)

SecureFalcon: Are We There Yet in Automated Software Vulnerability Detection with LLMs?
por: Ferrag, Mohamed Amine, et al.
Publicado: (2023)

PARASITE: Conditional System Prompt Poisoning to Hijack LLMs
por: Pham, Viet, et al.
Publicado: (2025)

BugWhisperer: Fine-Tuning LLMs for SoC Hardware Vulnerability Detection
por: Tarek, Shams, et al.
Publicado: (2025)

Are LLMs Vulnerable to Preference-Undermining Attacks (PUA)? A Factorial Analysis Methodology for Diagnosing the Trade-off between Preference Alignment and Real-World Validity
por: An, Hongjun, et al.
Publicado: (2026)

Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks
por: Dahiya, Vivek, et al.
Publicado: (2026)

Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models
por: Shan, Shawn, et al.
Publicado: (2023)

RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis
por: Tan, Xue, et al.
Publicado: (2024)

Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attacks
por: Xie, Chulin, et al.
Publicado: (2022)

Silent Sabotage During Fine-Tuning: Few-Shot Rationale Poisoning of Compact Medical LLMs
por: Xie, Jingyuan, et al.
Publicado: (2026)

On the Feasibility of Poisoning Text-to-Image AI Models via Adversarial Mislabeling
por: Wu, Stanley, et al.
Publicado: (2025)

When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output
por: Zhang, Shuoming, et al.
Publicado: (2025)

Mining Characteristics of Vulnerable Smart Contracts Across Lifecycle Stages
por: Peng, Hongli, et al.
Publicado: (2025)

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
por: Dziemian, Mateusz, et al.
Publicado: (2026)

Class-Conditional Neural Polarizer: A Lightweight and Effective Backdoor Defense by Purifying Poisoned Features
por: Zhu, Mingli, et al.
Publicado: (2025)

Proactive Detection of Physical Inter-rule Vulnerabilities in IoT Services Using a Deep Learning Approach
por: Huang, Bing, et al.
Publicado: (2024)

VerilogLAVD: LLM-Aided Rule Generation for Vulnerability Detection in Verilog
por: Long, Xiang, et al.
Publicado: (2025)

Poison to Detect: Detection of Targeted Overfitting in Federated Learning
por: Mestari, Soumia Zohra El, et al.
Publicado: (2025)