Cover Image

Say It Differently: Linguistic Styles as Jailbreak Vectors

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Panda, Srikant, Rai, Avinash
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AccessEval: Benchmarking Disability Bias in Large Language Models
by: Panda, Srikant, et al.
Published: (2025)

Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding
by: Joo, Seongho, et al.
Published: (2025)

Jailbreaking to Jailbreak
by: Kritz, Jeremy, et al.
Published: (2025)

A Multi-Task Role-Playing Agent Capable of Imitating Character Linguistic Styles
by: Chen, Siyuan, et al.
Published: (2024)

DAIQ: Auditing Demographic Attribute Inference from Question in LLMs
by: Panda, Srikant, et al.
Published: (2025)

Clinical QA 2.0: Multi-Task Learning for Answer Extraction and Categorization
by: Pattnayak, Priyaranjan, et al.
Published: (2025)

Efficient LLM-Jailbreaking via Multimodal-LLM Jailbreak
by: Ji, Haoxuan, et al.
Published: (2024)

Support-Contra Asymmetry in LLM Explanations
by: Patil, Avinash
Published: (2025)

EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models
by: Zhou, Weikang, et al.
Published: (2024)

Many-Turn Jailbreaking
by: Yang, Xianjun, et al.
Published: (2025)

Embedding Style Beyond Topics: Analyzing Dispersion Effects Across Different Language Models
by: Icard, Benjamin, et al.
Published: (2025)

When Informal Text Breaks NLI: Tokenization Failure, Distribution Shift, and Targeted Mitigations
by: Aluguvelly, Avinash Goutham
Published: (2026)

The Effectiveness of Style Vectors for Steering Large Language Models: A Human Evaluation
by: Diallo, Diaoulé, et al.
Published: (2026)

Exploring Performance Variations in Finetuned Translators of Ultra-Low Resource Languages: Do Linguistic Differences Matter?
by: Gonçalves, Isabel, et al.
Published: (2025)

Say Anything but This: When Tokenizer Betrays Reasoning in LLMs
by: Ayoobi, Navid, et al.
Published: (2026)

Chip-Tuning: Classify Before Language Models Say
by: Zhu, Fangwei, et al.
Published: (2024)

FS-DAG: Few Shot Domain Adapting Graph Networks for Visually Rich Document Understanding
by: Agarwal, Amit, et al.
Published: (2025)

Advancing Reasoning in Large Language Models: Promising Methods and Approaches
by: Patil, Avinash, et al.
Published: (2025)

Sarang at DEFACTIFY 4.0: Detecting AI-Generated Text Using Noised Data and an Ensemble of DeBERTa Models
by: Trivedi, Avinash, et al.
Published: (2025)

Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs
by: Camassa, Carolina, et al.
Published: (2026)

Uncovering the Persuasive Fingerprint of LLMs in Jailbreaking Attacks
by: Noughabi, Havva Alizadeh, et al.
Published: (2025)

Playing Language Game with LLMs Leads to Jailbreaking
by: Peng, Yu, et al.
Published: (2024)

Different Paths to Harmful Compliance: Behavioral Side Effects and Mechanistic Divergence Across LLM Jailbreaks
by: Kabir, Md Rysul, et al.
Published: (2026)

Cognitive-Mental-LLM: Evaluating Reasoning in Large Language Models for Mental Health Prediction via Online Text
by: Patil, Avinash, et al.
Published: (2025)

Saying the Unsaid: Revealing the Hidden Language of Multimodal Systems Through Telephone Games
by: Zhao, Juntu, et al.
Published: (2025)

From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves
by: Puerto, Haritz, et al.
Published: (2026)

Exploring Chinese Humor Generation: A Study on Two-Part Allegorical Sayings
by: Xu, Rongwu
Published: (2024)

A Blueprint for AI-Driven Software Quality: Integrating LLMs with Established Standards
by: Patil, Avinash
Published: (2025)

LLMs on a Budget? Say HOLA
by: Siddiqui, Zohaib Hasan, et al.
Published: (2025)

Foot-In-The-Door: A Multi-turn Jailbreak for LLMs
by: Weng, Zixuan, et al.
Published: (2025)

Poisoned LangChain: Jailbreak LLMs by LangChain
by: Wang, Ziqiu, et al.
Published: (2024)

Cross-Lingual Jailbreak Detection via Semantic Codebooks
by: Alanova, Shirin, et al.
Published: (2026)

Merging Improves Self-Critique Against Jailbreak Attacks
by: Gallego, Victor
Published: (2024)

From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreaking
by: Wang, Siyuan, et al.
Published: (2024)

Defending LLMs against Jailbreaking Attacks via Backtranslation
by: Wang, Yihan, et al.
Published: (2024)

Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility
by: Murphy, Brendan, et al.
Published: (2025)

The Art of Saying No: Contextual Noncompliance in Language Models
by: Brahman, Faeze, et al.
Published: (2024)

The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning
by: Li, Yubo, et al.
Published: (2026)

The Cost of Thinking: Increased Jailbreak Risk in Large Language Models
by: Yang, Fan
Published: (2025)

Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection
by: Giarrusso, Francesco, et al.
Published: (2025)