Cover Image

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yi, Biao, Huang, Tiansheng, Chen, Sishuo, Li, Tong, Liu, Zheli, Chu, Zhixuan, Li, Yiming
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning
by: Yi, Biao, et al.
Published: (2025)

Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks
by: Li, Boheng, et al.
Published: (2024)

Defense-as-a-Service: Black-box Shielding against Backdoored Graph Models
by: Yang, Xiao, et al.
Published: (2024)

BDFirewall: Towards Effective and Expeditiously Black-Box Backdoor Defense in MLaaS
by: Li, Ye, et al.
Published: (2025)

Query Provenance Analysis: Efficient and Robust Defense against Query-based Black-box Attacks
by: Li, Shaofei, et al.
Published: (2024)

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

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

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

Lite-BD: A Lightweight Black-box Backdoor Defense via Reviving Multi-Stage Image Transformations
by: Miah, Abdullah Arafat, et al.
Published: (2026)

AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents
by: Li, Yanjie, et al.
Published: (2025)

Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark
by: Fei, Zekun, et al.
Published: (2024)

TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models
by: Guo, Zhen, et al.
Published: (2026)

MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning Attacks
by: Chen, Tailun, et al.
Published: (2025)

Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models
by: Truong, Vu Tuan, et al.
Published: (2026)

FreeTalk:A plug-and-play and black-box defense against speech synthesis attacks
by: Pu, Yuwen, et al.
Published: (2025)

Hiding in Plain Sight: A Steganographic Approach to Stealthy LLM Jailbreaks
by: Geng, Jianing, et al.
Published: (2025)

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs
by: Li, Hongyi, et al.
Published: (2024)

KG-DF: A Black-box Defense Framework against Jailbreak Attacks Based on Knowledge Graphs
by: Liu, Shuyuan, et al.
Published: (2025)

WGLE:Backdoor-free and Multi-bit Black-box Watermarking for Graph Neural Networks
by: Li, Tingzhi, et al.
Published: (2025)

Inhibitory Attacks on Backdoor-based Fingerprinting for Large Language Models
by: Fu, Hang, et al.
Published: (2026)

EvoDefense: Co-Evolving Black-Box Defense with Large Language Models
by: Li, Yu, et al.
Published: (2026)

Dynamic Black-box Backdoor Attacks on IoT Sensory Data
by: Chathoth, Ajesh Koyatan, et al.
Published: (2025)

BeDKD: Backdoor Defense Based on Directional Mapping Module and Adversarial Knowledge Distillation
by: Wu, Zhengxian, et al.
Published: (2025)

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

NSmark: Null Space Based Black-box Watermarking Defense Framework for Language Models
by: Zhao, Haodong, et al.
Published: (2024)

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

Distributed Backdoor Attacks on Federated Graph Learning and Certified Defenses
by: Yang, Yuxin, et al.
Published: (2024)

Plato's Form: Toward Backdoor Defense-as-a-Service for LLMs with Prototype Representations
by: Chen, Chen, et al.
Published: (2026)

Towards Imperceptible Adversarial Defense: A Gradient-Driven Shield against Facial Manipulations
by: Li, Yue, et al.
Published: (2025)

Defenses at Odds: Measuring and Explaining Defense Conflicts in Large Language Models
by: Meng, Xiangtao, et al.
Published: (2026)

AEIOU: A Unified Defense Framework against NSFW Prompts in Text-to-Image Models
by: Wang, Yiming, et al.
Published: (2024)

MalModel: Hiding Malicious Payload in Mobile Deep Learning Models with Black-box Backdoor Attack
by: Hua, Jiayi, et al.
Published: (2024)

Understanding the Effects of Safety Unalignment on Large Language Models
by: Halloran, John T.
Published: (2026)

BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Models
by: Yan, Xiaobei, et al.
Published: (2025)

BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation
by: Yu, Haiyang, et al.
Published: (2024)

SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs
by: Wu, Zhengxian, et al.
Published: (2025)

Attack as Defense: Run-time Backdoor Implantation for Image Content Protection
by: Zhang, Haichuan, et al.
Published: (2024)

Black-box Membership Inference Attacks against Fine-tuned Diffusion Models
by: Pang, Yan, et al.
Published: (2023)

External Data Extraction Attacks against Retrieval-Augmented Large Language Models
by: He, Yu, et al.
Published: (2025)