Cover Image

Chainwash: Multi-Step Rewriting Attacks on Diffusion Language Model Watermarks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ameen, Mohd Ruhul, Islam, Akif, Mahmud, Nadim, Hamid, Md. Ekramul
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Parameter-Efficient Fine-Tuning for Low-Resource Languages: A Comparative Study of LLMs for Bengali Hate Speech Detection
by: Islam, Akif, et al.
Published: (2025)

Balancing Interpretability and Performance in Motor Imagery EEG Classification: A Comparative Study of ANFIS-FBCSP-PSO and EEGNet
by: Aktar, Farjana, et al.
Published: (2025)

Detecting AI-Generated Images via Diffusion Snap-Back Reconstruction: A Forensic Approach
by: Ameen, Mohd Ruhul, et al.
Published: (2025)

Empirical Evidence of Complexity-Induced Limits in Large Language Models on Finite Discrete State-Space Problems with Explicit Validity Constraints
by: Utsho, Md. Fahad Ullah, et al.
Published: (2026)

Towards a Humanized Social-Media Ecosystem: AI-Augmented HCI Design Patterns for Safety, Agency & Well-Being
by: Ameen, Mohd Ruhul, et al.
Published: (2025)

BengaliSent140: A Large-Scale Bengali Binary Sentiment Dataset for Hate and Non-Hate Speech Classification
by: Islam, Akif, et al.
Published: (2026)

KrishokBondhu: A Retrieval-Augmented Voice-Based Agricultural Advisory Call Center for Bengali Farmers
by: Ameen, Mohd Ruhul, et al.
Published: (2025)

CountFormer: A Transformer Framework for Learning Visual Repetition and Structure in Class-Agnostic Object Counting
by: Hossain, Md Tanvir, et al.
Published: (2025)

How News Feels: Understanding Affective Bias in Multilingual Headlines for Human-Centered Media Design
by: Ameen, Mohd Ruhul, et al.
Published: (2025)

Khelte Khelte Shikhi: A Proposed HCI Framework for Gamified Interactive Learning with Minecraft in Bangladeshi Education Systems
by: Ameen, Mohd Ruhul, et al.
Published: (2025)

QASecClaw: A Multi-Agent LLM Approach for False Positive Reduction in Static Application Security Testing
by: Ameen, Mohd Ruhul, et al.
Published: (2026)

When Denoising Hinders: Revisiting Zero-Shot ASR with SAM-Audio and Whisper
by: Islam, Akif, et al.
Published: (2026)

Automated Wicket-Taking Delivery Segmentation and Trajectory-Based Dismissal-Zone Analysis in Cricket Videos Using OCR-Guided YOLOv8
by: Karmoker, Joy, et al.
Published: (2025)

Critical Thinking in the Age of Artificial Intelligence: A Survey-Based Study with Machine Learning Insights
by: Bari, M Murshidul, et al.
Published: (2026)

When Words Don't Mean What They Say: Figurative Understanding in Bengali Idioms
by: Sakhawat, Adib, et al.
Published: (2026)

Oitijjo-3D: Generative AI Framework for Rapid 3D Heritage Reconstruction from Street View Imagery
by: Ope, Momen Khandoker, et al.
Published: (2025)

Teaching Machine Learning Through Cricket: A Practical Engineering Education Approach
by: Ameen, Mohd Ruhul, et al.
Published: (2025)

From Pixels to People: Satellite-Based Mapping and Quantification of Riverbank Erosion and Lost Villages in Bangladesh
by: Rafat, M Saifuzzaman, et al.
Published: (2025)

A Multi-Agent LLM Defense Pipeline Against Prompt Injection Attacks
by: Hossain, S M Asif, et al.
Published: (2025)

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks
by: Cheng, Yixin, et al.
Published: (2025)

Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models
by: Ringel, Liran, et al.
Published: (2026)

BanglaSentNet: An Explainable Hybrid Deep Learning Framework for Multi-Aspect Sentiment Analysis with Cross-Domain Transfer Learning
by: Islam, Ariful, et al.
Published: (2025)

Graph Elicitation for Guiding Multi-Step Reasoning in Large Language Models
by: Park, Jinyoung, et al.
Published: (2023)

LR-DWM: Efficient Watermarking for Diffusion Language Models
by: Raban, Ofek, et al.
Published: (2026)

Application of Multimodal Large Language Models in Autonomous Driving
by: Islam, Md Robiul
Published: (2024)

Mixed-Distil-BERT: Code-mixed Language Modeling for Bangla, English, and Hindi
by: Raihan, Md Nishat, et al.
Published: (2023)

BanglaIPA: Towards Robust Text-to-IPA Transcription with Contextual Rewriting in Bengali
by: Hasan, Jakir, et al.
Published: (2026)

Transformer-Driven Triple Fusion Framework for Enhanced Multimodal Author Intent Classification in Low-Resource Bangla
by: Islam, Ariful, et al.
Published: (2025)

Prompt Control-Flow Integrity: A Priority-Aware Runtime Defense Against Prompt Injection in LLM Systems
by: Alam, Md Takrim Ul, et al.
Published: (2026)

Parameter-Efficient Fine-Tuning of Large Language Models using Semantic Knowledge Tuning
by: Prottasha, Nusrat Jahan, et al.
Published: (2024)

BenHalluEval: A Multi-Task Hallucination Evaluation Framework for Large Language Models on Bengali
by: Adib, Shefayat E Shams, et al.
Published: (2026)

3D MRI-Based Alzheimer's Disease Classification Using Multi-Modal 3D CNN with Leakage-Aware Subject-Level Evaluation
by: Sifat, Md, et al.
Published: (2026)

BanglaLorica: Design and Evaluation of a Robust Watermarking Algorithm for Large Language Models in Bangla Text Generation
by: Tariqul, Amit Bin, et al.
Published: (2026)

Beyond Ray-Casting: Evaluating Controller, Free-Hand, and Virtual-Touch Modalities for Immersive Text Entry
by: Hossain, Md. Tanvir, et al.
Published: (2026)

Political Alignment in Large Language Models: A Multidimensional Audit of Psychometric Identity and Behavioral Bias
by: Sakhawat, Adib, et al.
Published: (2026)

Learnable Linguistic Watermarks for Tracing Model Extraction Attacks on Large Language Models
by: Bai, Minhao, et al.
Published: (2024)

Stylometric Watermarks for Large Language Models
by: Niess, Georg, et al.
Published: (2024)

Ensemble Watermarks for Large Language Models
by: Niess, Georg, et al.
Published: (2024)

In-Context Watermarks for Large Language Models
by: Liu, Yepeng, et al.
Published: (2025)

Incorporating Self-Rewriting into Large Language Model Reasoning Reinforcement
by: Yao, Jiashu, et al.
Published: (2025)