Cover Image

BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rachapudi, Jagadeesh, Vatsi, Ritali, Singh, Pranav, Hambarde, Praful, Shukla, Amit
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

RePAIR: Interactive Machine Unlearning through Prompt-Aware Model Repair
by: Rachapudi, Jagadeesh, et al.
Published: (2026)

BID-LoRA: A Parameter-Efficient Framework for Continual Learning and Unlearning
by: Rachapudi, Jagadeesh, et al.
Published: (2026)

Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models
by: Li, Haoran, et al.
Published: (2024)

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

Turning Your Strength into Watermark: Watermarking Large Language Model via Knowledge Injection
by: Li, Shuai, et al.
Published: (2023)

Transferring Backdoors between Large Language Models by Knowledge Distillation
by: Cheng, Pengzhou, et al.
Published: (2024)

VOW: Verifiable and Oblivious Watermark Detection for Large Language Models
by: Luan, Xiaokun, et al.
Published: (2026)

SeDT: Sentence-Transformer Decision-Transformer Conditioning for Multi-Turn Conversation Reliability
by: Setti, Ramakrishna Vamsi, et al.
Published: (2026)

Backdooring Bias in Large Language Models
by: Das, Anudeep, et al.
Published: (2026)

Protecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarking
by: Kong, Cong, et al.
Published: (2024)

A Nested Watermark for Large Language Models
by: Nagatsuka, Koichi, et al.
Published: (2025)

PRIVMARK: Private Large Language Models Watermarking with MPC
by: Fargues, Thomas, et al.
Published: (2025)

A Certified Robust Watermark For Large Language Models
by: Feng, Xianheng, et al.
Published: (2024)

Harmless Backdoor-based Client-side Watermarking in Federated Learning
by: Luo, Kaijing, et al.
Published: (2024)

zkFi: Privacy-Preserving and Regulation Compliant Transactions using Zero Knowledge Proofs
by: Chaudhary, Amit
Published: (2023)

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

Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models
by: Li, Xi, et al.
Published: (2024)

BadTemplate: A Training-Free Backdoor Attack via Chat Template Against Large Language Models
by: Wang, Zihan, et al.
Published: (2026)

MorphMark: Flexible Adaptive Watermarking for Large Language Models
by: Wang, Zongqi, et al.
Published: (2025)

Watermarking Text Data on Large Language Models for Dataset Copyright
by: Liu, Yixin, et al.
Published: (2023)

EditMark: Watermarking Large Language Models based on Model Editing
by: Li, Shuai, et al.
Published: (2025)

An End-to-End Model for Logits-Based Large Language Models Watermarking
by: Wong, Kahim, et al.
Published: (2025)

A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models
by: Wu, Yihan, et al.
Published: (2023)

ShapeMark: Robust and Diversity-Preserving Watermarking for Diffusion Models
by: Qian, Yuqi, et al.
Published: (2026)

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

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models
by: Yuan, Zenghui, et al.
Published: (2025)

On the Weaknesses of Backdoor-based Model Watermarking: An Information-theoretic Perspective
by: Hu, Aoting, et al.
Published: (2024)

Signal Watermark on Large Language Models
by: Xu, Zhenyu, et al.
Published: (2024)

Coward: Collision-based OOD Watermarking for Practical Proactive Federated Backdoor Detection
by: Li, Wenjie, et al.
Published: (2025)

Forging the Unforgeable: On the Feasibility of Counterfeit Watermarks in Backdoor-Based Dataset Ownership Verification
by: Li, Zhiying, et al.
Published: (2024)

Let Watermarks Speak: A Robust and Unforgeable Watermark for Language Models
by: Bai, Minhao
Published: (2024)

Double Backdoored: Converting Code Large Language Model Backdoors to Traditional Malware via Adversarial Instruction Tuning Attacks
by: Hossen, Md Imran, et al.
Published: (2024)

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

Black-Box Detection of Language Model Watermarks
by: Gloaguen, Thibaud, et al.
Published: (2024)

A Robust Semantics-based Watermark for Large Language Model against Paraphrasing
by: Ren, Jie, et al.
Published: (2023)

Yet Another Watermark for Large Language Models
by: Bao, Siyuan, et al.
Published: (2025)

Functional Subspace Watermarking for Large Language Models
by: Ding, Zikang, et al.
Published: (2026)

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

Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models
by: Ni, Zhenyang, et al.
Published: (2024)

Asking Back: Interaction-Layer Antidistillation Watermarks
by: Yang, Guang, et al.
Published: (2026)