Cover Image

Broken-Token: Filtering Obfuscated Prompts by Counting Characters-Per-Token

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zychlinski, Shaked, Kainan, Yuval
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language Information Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Whole New World: Creating a Parallel-Poisoned Web Only AI-Agents Can See
by: Zychlinski, Shaked
Published: (2025)

Do Stop Me Now: Detecting Boilerplate Responses with a Single Iteration
by: Kainan, Yuval, et al.
Published: (2025)

EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMs
by: Lin, Sam, et al.
Published: (2024)

Token-wise Influential Training Data Retrieval for Large Language Models
by: Lin, Huawei, et al.
Published: (2024)

HeavyWater and SimplexWater: Distortion-Free LLM Watermarks for Low-Entropy Next-Token Predictions
by: Tsur, Dor, et al.
Published: (2025)

Can LLMs Obfuscate Code? A Systematic Analysis of Large Language Models into Assembly Code Obfuscation
by: Mohseni, Seyedreza, et al.
Published: (2024)

Auditing Pay-Per-Token in Large Language Models
by: Velasco, Ander Artola, et al.
Published: (2025)

Token-level Data Selection for Safe LLM Fine-tuning
by: Li, Yanping, et al.
Published: (2026)

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?
by: Mu, Junjie, et al.
Published: (2025)

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

Every Character Counts: From Vulnerability to Defense in Phishing Detection
by: Chiper, Maria, et al.
Published: (2025)

Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearning
by: Lee, Hong kyu, et al.
Published: (2025)

STShield: Single-Token Sentinel for Real-Time Jailbreak Detection in Large Language Models
by: Wang, Xunguang, et al.
Published: (2025)

Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense
by: Ouyang, Yang, et al.
Published: (2025)

Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage
by: Hoque, Shahinul, et al.
Published: (2026)

Large Multimodal Agents for Accurate Phishing Detection with Enhanced Token Optimization and Cost Reduction
by: Trad, Fouad, et al.
Published: (2024)

Forgetting-MarI: LLM Unlearning via Marginal Information Regularization
by: Xu, Shizhou, et al.
Published: (2025)

OD-Stega: LLM-Based Relatively Secure Steganography via Optimized Distributions
by: Huang, Yu-Shin, et al.
Published: (2024)

A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring
by: Anwar, Usman, et al.
Published: (2026)

Protecting Privacy in Classifiers by Token Manipulation
by: Harel, Re'em, et al.
Published: (2024)

Token-Level Privacy in Large Language Models
by: Harel, Re'em, et al.
Published: (2025)

Interpreting the Repeated Token Phenomenon in Large Language Models
by: Yona, Itay, et al.
Published: (2025)

Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
by: Fang, Zheng, et al.
Published: (2026)

SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters
by: Yang, Yan, et al.
Published: (2024)

A Generative Approach to LLM Harmfulness Mitigation with Red Flag Tokens
by: Dobre, David, et al.
Published: (2025)

Token-Efficient Prompt Injection Attack: Provoking Cessation in LLM Reasoning via Adaptive Token Compression
by: Cui, Yu, et al.
Published: (2025)

How Different Tokenization Algorithms Impact LLMs and Transformer Models for Binary Code Analysis
by: Mostafa, Ahmed, et al.
Published: (2025)

DePrompt: Desensitization and Evaluation of Personal Identifiable Information in Large Language Model Prompts
by: Sun, Xiongtao, et al.
Published: (2024)

Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures
by: Su, Yanghao, et al.
Published: (2026)

NeuroFilter: Privacy Guardrails for Conversational LLM Agents
by: Das, Saswat, et al.
Published: (2026)

Prompt Injection as Role Confusion
by: Ye, Charles, et al.
Published: (2026)

ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets
by: Frikha, Ahmed, et al.
Published: (2024)

Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning
by: Ostermann, Simon, et al.
Published: (2024)

PII-Bench: Evaluating Query-Aware Privacy Protection Systems
by: Shen, Hao, et al.
Published: (2025)

TITAN: Graph-Executable Reasoning for Cyber Threat Intelligence
by: Simoni, Marco, et al.
Published: (2025)

DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation
by: Gong, Yuyang, et al.
Published: (2026)

Improving User Privacy in Personalized Generation: Client-Side Retrieval-Augmented Modification of Server-Side Generated Speculations
by: Salemi, Alireza, et al.
Published: (2026)

One Single Hub Text Breaks CLIP: Identifying Vulnerabilities in Cross-Modal Encoders via Hubness
by: Deguchi, Hiroyuki, et al.
Published: (2026)

SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
by: Mishra, Saroj, et al.
Published: (2026)

Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models
by: Zheng, Yujia, et al.
Published: (2025)