Image de couverture de livre

Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yan, Jun, Yadav, Vikas, Li, Shiyang, Chen, Lichang, Tang, Zheng, Wang, Hai, Srinivasan, Vijay, Ren, Xiang, Jin, Hongxia
Format:	Preprint
Publié:	2023
Sujets:	Computation and Language Cryptography and Security Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Double Backdoored: Converting Code Large Language Model Backdoors to Traditional Malware via Adversarial Instruction Tuning Attacks
par: Hossen, Md Imran, et autres
Publié: (2024)

Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
par: Xu, Jiashu, et autres
Publié: (2023)

Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models
par: Clop, Cody, et autres
Publié: (2024)

Rethinking Backdoor Detection Evaluation for Language Models
par: Yan, Jun, et autres
Publié: (2024)

Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods
par: Chen, Yulin, et autres
Publié: (2025)

BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
par: Xiang, Zhen, et autres
Publié: (2024)

Defending against Indirect Prompt Injection by Instruction Detection
par: Wen, Tongyu, et autres
Publié: (2025)

BaThe: Defense against the Jailbreak Attack in Multimodal Large Language Models by Treating Harmful Instruction as Backdoor Trigger
par: Chen, Yulin, et autres
Publié: (2024)

ProtegoFed: Backdoor-Free Federated Instruction Tuning with Interspersed Poisoned Data
par: Zhao, Haodong, et autres
Publié: (2026)

Mitigating Indirect Prompt Injection via Instruction-Following Intent Analysis
par: Kang, Mintong, et autres
Publié: (2025)

Revisiting Backdoor Threat in Federated Instruction Tuning from a Signal Aggregation Perspective
par: Zhao, Haodong, et autres
Publié: (2026)

TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
par: He, Xuanli, et autres
Publié: (2024)

Evaluation of Prompt Injection Defenses in Large Language Models
par: Deep, Priyal, et autres
Publié: (2026)

AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization
par: Ying, Zonghao, et autres
Publié: (2026)

Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction
par: Chen, Yulin, et autres
Publié: (2025)

Krait: A Backdoor Attack Against Graph Prompt Tuning
par: Song, Ying, et autres
Publié: (2024)

Goal-guided Generative Prompt Injection Attack on Large Language Models
par: Zhang, Chong, et autres
Publié: (2024)

Robust Anti-Backdoor Instruction Tuning in LVLMs
par: Xun, Yuan, et autres
Publié: (2025)

Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models
par: Ni, Zhenyang, et autres
Publié: (2024)

AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks
par: Jia, Yuqi, et autres
Publié: (2026)

DRIP: Defending Prompt Injection via Token-wise Representation Editing and Residual Instruction Fusion
par: Liu, Ruofan, et autres
Publié: (2025)

XuanJia: A Comprehensive Virtualization-Based Code Obfuscator for Binary Protection
par: Zou, Xianyu, et autres
Publié: (2026)

Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
par: Cao, Yuanpu, et autres
Publié: (2023)

Decoding Latent Attack Surfaces in LLMs: Prompt Injection via HTML in Web Summarization
par: Verma, Ishaan, et autres
Publié: (2025)

ASPIRER: Bypassing System Prompts With Permutation-based Backdoors in LLMs
par: Yan, Lu, et autres
Publié: (2024)

Injection, Attack and Erasure: Revocable Backdoor Attacks via Machine Unlearning
par: Song, Baogang, et autres
Publié: (2025)

A Novel Evaluation Framework for Assessing Resilience Against Prompt Injection Attacks in Large Language Models
par: Yip, Daniel Wankit, et autres
Publié: (2024)

Prompt Injection as an Emerging Threat: Evaluating the Resilience of Large Language Models
par: Ganiuly, Daniyal, et autres
Publié: (2025)

AttackEval: A Systematic Empirical Study of Prompt Injection Attack Effectiveness Against Large Language Models
par: Wang, Jackson
Publié: (2026)

Misleading Large Language Models used (or misused) in Scientific Peer-Reviewing via Hidden Prompt-Injection Attacks
par: Collu, Matteo Gioele, et autres
Publié: (2025)

PromptShield: Deployable Detection for Prompt Injection Attacks
par: Jacob, Dennis, et autres
Publié: (2025)

Cross-Modal Backdoors in Multimodal Large Language Models
par: Wang, Runhe, et autres
Publié: (2026)

Defense Against Prompt Injection Attack by Leveraging Attack Techniques
par: Chen, Yulin, et autres
Publié: (2024)

DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection
par: Ren, Junyu, et autres
Publié: (2026)

ARGUS: Defending Against Multimodal Indirect Prompt Injection via Steering Instruction-Following Behavior
par: Lu, Weikai, et autres
Publié: (2025)

Prompt Injection Attacks on Large Language Models in Oncology
par: Clusmann, Jan, et autres
Publié: (2024)

Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding
par: Pathade, Chetan
Publié: (2025)

Inhibitory Attacks on Backdoor-based Fingerprinting for Large Language Models
par: Fu, Hang, et autres
Publié: (2026)

Transferring Backdoors between Large Language Models by Knowledge Distillation
par: Cheng, Pengzhou, et autres
Publié: (2024)

On the Adversarial Robustness of Instruction-Tuned Large Language Models for Code
par: Hossen, Md Imran, et autres
Publié: (2024)