Cover Image

Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Sheng, Sheng, Qiang, Wang, Danding, Li, Yang, Yang, Guang, Cao, Juan
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration
by: Li, Qintong, et al.
Published: (2024)

LLM-Generated Fake News Induces Truth Decay in News Ecosystem: A Case Study on Neural News Recommendation
by: Hu, Beizhe, et al.
Published: (2025)

Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained LLM-Generated Text Detection
by: Li, Yang, et al.
Published: (2026)

Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discovery
by: Sun, Yifan, et al.
Published: (2025)

The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas
by: Wu, Ya, et al.
Published: (2025)

Exploiting User Comments for Early Detection of Fake News Prior to Users' Commenting
by: Nan, Qiong, et al.
Published: (2023)

Reasoning About the Unsaid: Misinformation Detection with Omission-Aware Graph Inference
by: Wang, Zhengjia, et al.
Published: (2025)

Bridging Thoughts and Words: Graph-Based Intent-Semantic Joint Learning for Fake News Detection
by: Wang, Zhengjia, et al.
Published: (2025)

Let Silence Speak: Enhancing Fake News Detection with Generated Comments from Large Language Models
by: Nan, Qiong, et al.
Published: (2024)

Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection
by: Hu, Beizhe, et al.
Published: (2023)

Exploring news intent and its application: A theory-driven approach
by: Wang, Zhengjia, et al.
Published: (2023)

Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments
by: Mi, Hao, et al.
Published: (2026)

Ten Words Only Still Help: Improving Black-Box AI-Generated Text Detection via Proxy-Guided Efficient Re-Sampling
by: Shi, Yuhui, et al.
Published: (2024)

From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring
by: Li, Yang, et al.
Published: (2025)

UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models
by: Oh, Sejoon, et al.
Published: (2024)

MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety
by: Yang, Yahan, et al.
Published: (2025)

Paper Summary Attack: Jailbreaking LLMs through LLM Safety Papers
by: Lin, Liang, et al.
Published: (2025)

SMILES-Prompting: A Novel Approach to LLM Jailbreak Attacks in Chemical Synthesis
by: Wong, Aidan, et al.
Published: (2024)

ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails
by: Wang, Yan, et al.
Published: (2026)

PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
by: Shen, Guobin, et al.
Published: (2025)

Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection
by: Wei, Zhipeng, et al.
Published: (2024)

Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
by: Wang, Jiongxiao, et al.
Published: (2024)

ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts
by: Aswal, Darpan, et al.
Published: (2025)

ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
by: Mou, Yutao, et al.
Published: (2026)

Benchmarking LLM Guardrails in Handling Multilingual Toxicity
by: Yang, Yahan, et al.
Published: (2024)

Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?
by: Xin, Yuan, et al.
Published: (2025)

"Moralized" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks
by: Wang, Libo
Published: (2024)

CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety
by: An, Heajun, et al.
Published: (2026)

Enhancing Jailbreak Attacks with Diversity Guidance
by: Zhang, Xu, et al.
Published: (2024)

Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing
by: Zhao, Yinzhi, et al.
Published: (2026)

SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks
by: Cao, Hongye, et al.
Published: (2025)

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

TWGuard: A Case Study of LLM Safety Guardrails for Localized Linguistic Contexts
by: Chu, Hua-Rong, et al.
Published: (2026)

MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
by: Song, Jialin, et al.
Published: (2026)

Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation
by: Li, Qizhang, et al.
Published: (2024)

AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation
by: Wang, Zijun, et al.
Published: (2024)

JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
by: Chu, Junjie, et al.
Published: (2024)

PhantomHunter: Detecting Unseen Privately-Tuned LLM-Generated Text via Family-Aware Learning
by: Shi, Yuhui, et al.
Published: (2025)

SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance
by: Huang, Caishuang, et al.
Published: (2024)

Black-Box Guardrail Reverse-engineering Attack
by: Yao, Hongwei, et al.
Published: (2025)