Copertina

TokenBreak: Bypassing Text Classification Models Through Token Manipulation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Schulz, Kasimir, Yeung, Kenneth, Evans, Kieran
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ShadowGenes: Leveraging Recurring Patterns within Computational Graphs for Model Genealogy
di: Schulz, Kasimir, et al.
Pubblicazione: (2025)

TokenProber: Jailbreaking Text-to-image Models via Fine-grained Word Impact Analysis
di: Wang, Longtian, et al.
Pubblicazione: (2025)

No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
di: Kazdan, Joshua, et al.
Pubblicazione: (2025)

Knowledge Return Oriented Prompting (KROP)
di: Martin, Jason, et al.
Pubblicazione: (2024)

Adaptively Private Next-Token Prediction of Large Language Models
di: Flemings, James, et al.
Pubblicazione: (2024)

Cascade: Token-Sharded Private LLM Inference
di: Thomas, Rahul, et al.
Pubblicazione: (2025)

Token-Efficient Change Detection in LLM APIs
di: Chauvin, Timothée, et al.
Pubblicazione: (2026)

Traveling Salesman-Based Token Ordering Improves Stability in Homomorphically Encrypted Language Models
di: Rho, Donghwan, et al.
Pubblicazione: (2025)

Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment
di: Zaree, Pedram, et al.
Pubblicazione: (2025)

Real-Time Privacy Risk Measurement with Privacy Tokens for Gradient Leakage
di: Meng, Jiayang, et al.
Pubblicazione: (2025)

Vision Transformer with Adversarial Indicator Token against Adversarial Attacks in Radio Signal Classifications
di: Zhang, Lu, et al.
Pubblicazione: (2025)

Tricking Retrievers with Influential Tokens: An Efficient Black-Box Corpus Poisoning Attack
di: Wang, Cheng, et al.
Pubblicazione: (2025)

Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification
di: Zhang, Boyang, et al.
Pubblicazione: (2024)

Differentially Private Next-Token Prediction of Large Language Models
di: Flemings, James, et al.
Pubblicazione: (2024)

One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
di: Zhang, Mohan, et al.
Pubblicazione: (2025)

Bypassing Prompt Guards in Production with Controlled-Release Prompting
di: Fairoze, Jaiden, et al.
Pubblicazione: (2025)

Constructing Multi-label Hierarchical Classification Models for MITRE ATT&CK Text Tagging
di: Crossman, Andrew, et al.
Pubblicazione: (2026)

Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
di: Huo, Mingjia, et al.
Pubblicazione: (2024)

MambaNetBurst: Direct Byte-level Network Traffic Classification without Tokenization or Pretraining
di: Kulatilleke, Gayan K., et al.
Pubblicazione: (2026)

Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens
di: Zhang, Anqi, et al.
Pubblicazione: (2024)

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift
di: Yuan, Shuai, et al.
Pubblicazione: (2025)

Efficient Differentially Private Fine-Tuning of Diffusion Models
di: Liu, Jing, et al.
Pubblicazione: (2024)

BlocksecRT-DETR: Decentralized Privacy-Preserving and Token-Efficient Federated Transformer Learning for Secure Real-Time Object Detection in ITS
di: Tahera, Mohoshin Ara, et al.
Pubblicazione: (2026)

Breaking Distortion-free Watermarks in Large Language Models
di: Reynolds, Shayleen, et al.
Pubblicazione: (2025)

Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models
di: Zhang, Tianchen, et al.
Pubblicazione: (2024)

GRASP -- Graph-Based Anomaly Detection Through Self-Supervised Classification
di: Buchta, Robin, et al.
Pubblicazione: (2026)

Quantization Blindspots: How Model Compression Breaks Backdoor Defenses
di: Pandey, Rohan, et al.
Pubblicazione: (2025)

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

Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs
di: Chen, Wenyu, et al.
Pubblicazione: (2026)

Token-Modification Adversarial Attacks for Natural Language Processing: A Survey
di: Roth, Tom, et al.
Pubblicazione: (2021)

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

Predictive Auditing of Hidden Tokens in LLM APIs via Reasoning Length Estimation
di: Wang, Ziyao, et al.
Pubblicazione: (2025)

When the Same Coefficients Reach Different Places: Asymmetric Realizability in Transplanting Tokenizers across Large Language Models
di: Liu, Xiaoze, et al.
Pubblicazione: (2025)

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
di: Nasr, Milad, et al.
Pubblicazione: (2025)

RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation
di: Cheng, Zelei, et al.
Pubblicazione: (2024)

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation
di: Zhu, Wentian, et al.
Pubblicazione: (2025)

ShadowLogic: Backdoors in Any Whitebox LLM
di: Schulz, Kasimir, et al.
Pubblicazione: (2025)

Breaking Data Silos: Towards Open and Scalable Mobility Foundation Models via Generative Continual Learning
di: Yuan, Yuan, et al.
Pubblicazione: (2025)

Analyzing Inference Privacy Risks Through Gradients in Machine Learning
di: Li, Zhuohang, et al.
Pubblicazione: (2024)

Evading Black-box Classifiers Without Breaking Eggs
di: Debenedetti, Edoardo, et al.
Pubblicazione: (2023)