Imagen de Portada

BadJudge: Backdoor Vulnerabilities of LLM-as-a-Judge

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Tong, Terry, Wang, Fei, Zhao, Zhe, Chen, Muhao
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

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

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

Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges
por: Liu, Qin, et al.
Publicado: (2024)

Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges
por: Ding, Ruomeng, et al.
Publicado: (2026)

BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents
por: Wang, Yifei, et al.
Publicado: (2024)

Exploring Backdoor Vulnerabilities of Chat Models
por: Hao, Yunzhuo, et al.
Publicado: (2024)

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

ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Language Models
por: Owiredu-Ashley, Harry
Publicado: (2026)

Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
por: Yang, Wenkai, et al.
Publicado: (2024)

BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models
por: Xue, Jiaqi, et al.
Publicado: (2024)

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

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

Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model
por: Wu, Tianyi, et al.
Publicado: (2026)

Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents
por: Nawal, Aditya, et al.
Publicado: (2026)

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

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

The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)
por: Zeng, Shenglai, et al.
Publicado: (2024)

BadLLM-TG: A Backdoor Defender powered by LLM Trigger Generator
por: Zhang, Ruyi, et al.
Publicado: (2026)

Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization
por: Simoni, Marco, et al.
Publicado: (2025)

GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading Agents
por: Li, Xueyi, et al.
Publicado: (2026)

Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
por: Zhao, Shuai, et al.
Publicado: (2024)

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

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

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

Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
por: Zhao, Shuai, et al.
Publicado: (2024)

bi-GRPO: Bidirectional Optimization for Jailbreak Backdoor Injection on LLMs
por: Ji, Wence, et al.
Publicado: (2025)

Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers
por: Wei, Jiali, et al.
Publicado: (2026)

Instructional Fingerprinting of Large Language Models
por: Xu, Jiashu, et al.
Publicado: (2024)

When Reject Turns into Accept: Quantifying the Vulnerability of LLM-Based Scientific Reviewers to Indirect Prompt Injection
por: Sahoo, Devanshu, et al.
Publicado: (2025)

Breaking PEFT Limitations: Leveraging Weak-to-Strong Knowledge Transfer for Backdoor Attacks in LLMs
por: Zhao, Shuai, et al.
Publicado: (2024)

Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation
por: Schwartz, Daniel, et al.
Publicado: (2025)

Claim-Guided Textual Backdoor Attack for Practical Applications
por: Song, Minkyoo, et al.
Publicado: (2024)

Mapping the Exploitation Surface: A 10,000-Trial Taxonomy of What Makes LLM Agents Exploit Vulnerabilities
por: Mouzouni, Charafeddine
Publicado: (2026)

SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer
por: Cheng, Pengzhou, et al.
Publicado: (2024)

PentestJudge: Judging Agent Behavior Against Operational Requirements
por: Caldwell, Shane, et al.
Publicado: (2025)

Security in LLM-as-a-Judge: A Comprehensive SoK
por: Masoud, Aiman Al, et al.
Publicado: (2026)

Optimization-based Prompt Injection Attack to LLM-as-a-Judge
por: Shi, Jiawen, et al.
Publicado: (2024)

LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem
por: Liu, Hongyi, et al.
Publicado: (2024)

BadEdit: Backdooring large language models by model editing
por: Li, Yanzhou, et al.
Publicado: (2024)