Image de couverture de livre

Swallowing the Poison Pills: Insights from Vulnerability Disparity Among LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yifeng, Peng, Zhizheng, Wu, Chen, Chen
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

LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights
par: Sheng, Ze, et autres
Publié: (2025)

On The Dangers of Poisoned LLMs In Security Automation
par: Karlsen, Patrick, et autres
Publié: (2025)

Persistent Pre-Training Poisoning of LLMs
par: Zhang, Yiming, et autres
Publié: (2024)

Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks
par: Cotroneo, Domenico, et autres
Publié: (2023)

PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning
par: Fu, Tingchen, et autres
Publié: (2024)

Logic Meets Magic: LLMs Cracking Smart Contract Vulnerabilities
par: Xiao, ZeKe, et autres
Publié: (2025)

Data Poisoning Vulnerabilities Across Healthcare AI Architectures: A Security Threat Analysis
par: Abtahi, Farhad, et autres
Publié: (2025)

Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning
par: Yan, Shenao, et autres
Publié: (2026)

P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs
par: Zhao, Shuai, et autres
Publié: (2025)

From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs
par: Shen, Guangyu, et autres
Publié: (2025)

Decoding Deception: Understanding Automatic Speech Recognition Vulnerabilities in Evasion and Poisoning Attacks
par: G, Aravindhan, et autres
Publié: (2025)

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

CSC: Turning the Adversary's Poison against Itself
par: Shi, Yuchen, et autres
Publié: (2026)

Toward Polymorphic Backdoor against Semantic Communication via Intensity-Based Poisoning
par: Yang, Xiao, et autres
Publié: (2026)

Poisoned Acoustics
par: Dahme, Harrison
Publié: (2026)

Scaling Trends for Data Poisoning in LLMs
par: Bowen, Dillon, et autres
Publié: (2024)

LoopTrap: Termination Poisoning Attacks on LLM Agents
par: Xu, Huiyu, et autres
Publié: (2026)

Data Poisoning in Deep Learning: A Survey
par: Zhao, Pinlong, et autres
Publié: (2025)

Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense
par: Zhang, Jiawen, et autres
Publié: (2025)

Towards Compositional Generalization in LLMs for Smart Contract Security: A Case Study on Reentrancy Vulnerabilities
par: Zhou, Ying, et autres
Publié: (2026)

On the Effectiveness of Instruction-Tuning Local LLMs for Identifying Software Vulnerabilities
par: Park, Sangryu, et autres
Publié: (2025)

ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking
par: Wu, Yutao, et autres
Publié: (2025)

Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents
par: Zou, Wei, et autres
Publié: (2026)

SecureFalcon: Are We There Yet in Automated Software Vulnerability Detection with LLMs?
par: Ferrag, Mohamed Amine, et autres
Publié: (2023)

PARASITE: Conditional System Prompt Poisoning to Hijack LLMs
par: Pham, Viet, et autres
Publié: (2025)

BugWhisperer: Fine-Tuning LLMs for SoC Hardware Vulnerability Detection
par: Tarek, Shams, et autres
Publié: (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
par: An, Hongjun, et autres
Publié: (2026)

Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks
par: Dahiya, Vivek, et autres
Publié: (2026)

Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models
par: Shan, Shawn, et autres
Publié: (2023)

RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis
par: Tan, Xue, et autres
Publié: (2024)

Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attacks
par: Xie, Chulin, et autres
Publié: (2022)

Silent Sabotage During Fine-Tuning: Few-Shot Rationale Poisoning of Compact Medical LLMs
par: Xie, Jingyuan, et autres
Publié: (2026)

On the Feasibility of Poisoning Text-to-Image AI Models via Adversarial Mislabeling
par: Wu, Stanley, et autres
Publié: (2025)

When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output
par: Zhang, Shuoming, et autres
Publié: (2025)

Mining Characteristics of Vulnerable Smart Contracts Across Lifecycle Stages
par: Peng, Hongli, et autres
Publié: (2025)

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
par: Dziemian, Mateusz, et autres
Publié: (2026)

Class-Conditional Neural Polarizer: A Lightweight and Effective Backdoor Defense by Purifying Poisoned Features
par: Zhu, Mingli, et autres
Publié: (2025)

Proactive Detection of Physical Inter-rule Vulnerabilities in IoT Services Using a Deep Learning Approach
par: Huang, Bing, et autres
Publié: (2024)

VerilogLAVD: LLM-Aided Rule Generation for Vulnerability Detection in Verilog
par: Long, Xiang, et autres
Publié: (2025)

Poison to Detect: Detection of Targeted Overfitting in Federated Learning
par: Mestari, Soumia Zohra El, et autres
Publié: (2025)