Cover Image

Multi-Trigger Poisoning Amplifies Backdoor Vulnerabilities in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sivapiromrat, Sanhanat, Zhang, Caiqi, Basaldella, Marco, Collier, Nigel
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Privacy-R1: Privacy-Aware Multi-LLM Agent Collaboration via Reinforcement Learning
by: Hui, Zheng, et al.
Published: (2025)

Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs
by: Price, Sara, et al.
Published: (2024)

Universal Jailbreak Backdoors from Poisoned Human Feedback
by: Rando, Javier, et al.
Published: (2023)

Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Models
by: Yao, Duanyi, et al.
Published: (2026)

How Vulnerable Are Edge LLMs?
by: Ding, Ao, et al.
Published: (2026)

Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMs
by: Wang, Linlin, et al.
Published: (2025)

Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
by: Xu, Jiashu, et al.
Published: (2023)

Securing Multi-turn Conversational Language Models From Distributed Backdoor Triggers
by: Tong, Terry, et al.
Published: (2024)

BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers
by: Xue, Jiaqi, et al.
Published: (2024)

SteganoBackdoor: Stealthy and Data-Efficient Backdoor Attacks on Language Models
by: Xue, Eric, et al.
Published: (2025)

From Shortcuts to Triggers: Backdoor Defense with Denoised PoE
by: Liu, Qin, et al.
Published: (2023)

LUQ: Long-text Uncertainty Quantification for LLMs
by: Zhang, Caiqi, et al.
Published: (2024)

Turn-Based Structural Triggers: Prompt-Free Backdoors in Multi-Turn LLMs
by: Lu, Yiyang, et al.
Published: (2026)

WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection
by: Shetty, Anudeex, et al.
Published: (2024)

Composite Backdoor Attacks Against Large Language Models
by: Huang, Hai, et al.
Published: (2023)

Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment
by: Shao, Zedian, et al.
Published: (2024)

CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models
by: Zeng, Rui, et al.
Published: (2024)

Learning to Poison Large Language Models for Downstream Manipulation
by: Zhou, Xiangyu, et al.
Published: (2024)

Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
by: Betley, Jan, et al.
Published: (2025)

Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs
by: Rando, Javier, et al.
Published: (2024)

Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning
by: Zhang, Yujie, et al.
Published: (2024)

Architecture Matters: Comparing RAG Systems under Knowledge Base Poisoning
by: Korn, Samuel
Published: (2026)

Data-centric NLP Backdoor Defense from the Lens of Memorization
by: Wang, Zhenting, et al.
Published: (2024)

Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation
by: Chaudhari, Harsh, et al.
Published: (2024)

Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors
by: Chen, Yen-Shan, et al.
Published: (2025)

Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
by: Yan, Jun, et al.
Published: (2023)

Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models
by: He, Jiaming, et al.
Published: (2024)

Hardware-Triggered Backdoors
by: Möller, Jonas, et al.
Published: (2026)

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

When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents
by: Xu, Xiaoyu, et al.
Published: (2026)

Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions
by: Cinà, Antonio Emanuele, et al.
Published: (2021)

Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
by: Zhuang, Haomin, et al.
Published: (2023)

From Theory to Practice: Evaluating Data Poisoning Attacks and Defenses in In-Context Learning on Social Media Health Discourse
by: Jhuma, Rabeya Amin, et al.
Published: (2025)

STAR: Detecting Inference-time Backdoors in LLM Reasoning via State-Transition Amplification Ratio
by: Park, Seong-Gyu, et al.
Published: (2026)

Importing Phantoms: Measuring LLM Package Hallucination Vulnerabilities
by: Krishna, Arjun, et al.
Published: (2025)

Detecting and Understanding Vulnerabilities in Language Models via Mechanistic Interpretability
by: García-Carrasco, Jorge, et al.
Published: (2024)

Exploring Vulnerabilities and Protections in Large Language Models: A Survey
by: Liu, Frank Weizhen, et al.
Published: (2024)

Adversarial Data Poisoning for Fake News Detection: How to Make a Model Misclassify a Target News without Modifying It
by: Siciliano, Federico, et al.
Published: (2023)

Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks
by: Li, Yige, et al.
Published: (2024)

WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks
by: Shetty, Anudeex, et al.
Published: (2024)