Imagen de Portada

Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Haoran, Chen, Yulin, Zheng, Zihao, Hu, Qi, Chan, Chunkit, Liu, Heshan, Song, Yangqiu
Formato:	Preprint
Publicado:	2024
Materias:	Cryptography and Security Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Privacy in Large Language Models: Attacks, Defenses and Future Directions
por: Li, Haoran, et al.
Publicado: (2023)

BaThe: Defense against the Jailbreak Attack in Multimodal Large Language Models by Treating Harmful Instruction as Backdoor Trigger
por: Chen, Yulin, et al.
Publicado: (2024)

PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models
por: Li, Haoran, et al.
Publicado: (2023)

Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods
por: Chen, Yulin, et al.
Publicado: (2025)

GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory
por: Fan, Wei, et al.
Publicado: (2024)

Defense Against Prompt Injection Attack by Leveraging Attack Techniques
por: Chen, Yulin, et al.
Publicado: (2024)

Privacy Checklist: Privacy Violation Detection Grounding on Contextual Integrity Theory
por: Li, Haoran, et al.
Publicado: (2024)

Federated Domain-Specific Knowledge Transfer on Large Language Models Using Synthetic Data
por: Li, Haoran, et al.
Publicado: (2024)

Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks
por: Li, Ziqiang, et al.
Publicado: (2024)

TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models
por: Cheng, Pengzhou, et al.
Publicado: (2024)

TopicAttack: An Indirect Prompt Injection Attack via Topic Transition
por: Chen, Yulin, et al.
Publicado: (2025)

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
por: Yi, Biao, et al.
Publicado: (2025)

Privacy-Preserved Neural Graph Databases
por: Hu, Qi, et al.
Publicado: (2023)

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models
por: Wang, Zihan, et al.
Publicado: (2025)

Isolate Trigger: Detecting and Eliminating Adaptive Backdoor Attacks
por: Sun, Chengrui, et al.
Publicado: (2025)

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

ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models
por: Wang, Zihan, et al.
Publicado: (2025)

Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining
por: Wu, Zongru, et al.
Publicado: (2024)

Can Indirect Prompt Injection Attacks Be Detected and Removed?
por: Chen, Yulin, et al.
Publicado: (2025)

Rethinking Backdoor Detection Evaluation for Language Models
por: Yan, Jun, et al.
Publicado: (2024)

Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
por: Cao, Yuanpu, et al.
Publicado: (2023)

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

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

BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models
por: Rachapudi, Jagadeesh, et al.
Publicado: (2026)

Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
por: Wang, Jiongxiao, et al.
Publicado: (2024)

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

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
por: Jiang, Peihai, et al.
Publicado: (2025)

BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-box Large Language Models
por: Wu, Zhengxian, et al.
Publicado: (2025)

Cross-Modal Backdoors in Multimodal Large Language Models
por: Wang, Runhe, et al.
Publicado: (2026)

DUP: Detection-guided Unlearning for Backdoor Purification in Language Models
por: Hu, Man, et al.
Publicado: (2025)

UOR: Universal Backdoor Attacks on Pre-trained Language Models
por: Du, Wei, et al.
Publicado: (2023)

Resource Consumption Red-Teaming for Large Vision-Language Models
por: Gao, Haoran, et al.
Publicado: (2025)

Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning
por: Zhao, Shuai, et al.
Publicado: (2024)

A Survey of Recent Backdoor Attacks and Defenses in Large Language Models
por: Zhao, Shuai, et al.
Publicado: (2024)

BadActs: A Universal Backdoor Defense in the Activation Space
por: Yi, Biao, et al.
Publicado: (2024)

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

MBTSAD: Mitigating Backdoors in Language Models Based on Token Splitting and Attention Distillation
por: Ding, Yidong, et al.
Publicado: (2025)

Where Do Backdoors Live? A Component-Level Analysis of Backdoor Propagation in Speech Language Models
por: Fortier, Alexandrine, et al.
Publicado: (2025)

Task-Agnostic Detector for Insertion-Based Backdoor Attacks
por: Lyu, Weimin, et al.
Publicado: (2024)

WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents
por: Chen, Yulin, et al.
Publicado: (2026)