Imagen de Portada

Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Peng, Jingyu, Wang, Maolin, Wang, Nan, Li, Jiatong, Li, Yuchen, Ye, Yuyang, Wang, Wanyu, Jia, Pengyue, Zhang, Kai, Zhao, Xiangyu
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Stepwise Reasoning Error Disruption Attack of LLMs
por: Peng, Jingyu, et al.
Publicado: (2024)

MOSAIC: Composable Safety Alignment with Modular Control Tokens
por: Peng, Jingyu, et al.
Publicado: (2026)

Pre-train, Align, and Disentangle: Empowering Sequential Recommendation with Large Language Models
por: Wang, Yuhao, et al.
Publicado: (2024)

MTA: A Merge-then-Adapt Framework for Personalized Large Language Model
por: Li, Xiaopeng, et al.
Publicado: (2025)

Are LLMs Stable Formal Logic Translators in Logical Reasoning Across Linguistically Diversified Texts?
por: Li, Qingchuan, et al.
Publicado: (2025)

SIGMA: Selective Gated Mamba for Sequential Recommendation
por: Liu, Ziwei, et al.
Publicado: (2024)

AdaSwitch: Balancing Exploration and Guidance in Knowledge Distillation via Adaptive Switching
por: Peng, Jingyu, et al.
Publicado: (2025)

Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking
por: Xu, Nan, et al.
Publicado: (2023)

Behavior-Equivalent Token: Single-Token Replacement for Long Prompts in LLMs
por: Dong, Jiancheng, et al.
Publicado: (2025)

Renormalization Group Guided Tensor Network Structure Search
por: Wang, Maolin, et al.
Publicado: (2025)

LLM-EDT: Large Language Model Enhanced Cross-domain Sequential Recommendation with Dual-phase Training
por: Liu, Ziwei, et al.
Publicado: (2025)

Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuning
por: Han, Xiao, et al.
Publicado: (2025)

Adaptive Selection of Symbolic Languages for Improving LLM Logical Reasoning
por: Wang, Xiangyu, et al.
Publicado: (2025)

SafePlan: Leveraging Formal Logic and Chain-of-Thought Reasoning for Enhanced Safety in LLM-based Robotic Task Planning
por: Obi, Ike, et al.
Publicado: (2025)

DANCE: Resource-Efficient Neural Architecture Search with Data-Aware and Continuous Adaptation
por: Wang, Maolin, et al.
Publicado: (2025)

Scenario-Wise Rec: A Multi-Scenario Recommendation Benchmark
por: Li, Xiaopeng, et al.
Publicado: (2024)

Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning
por: Wang, Zhaoqi, et al.
Publicado: (2025)

Logic-Parametric Neuro-Symbolic NLI: Controlling Logical Formalisms for Verifiable LLM Reasoning
por: Farjami, Ali, et al.
Publicado: (2026)

Grzegorczyk Logic Unlocked
por: Wołoszyn, Wojciech Aleksander
Publicado: (2025)

Do Large Language Models Excel in Complex Logical Reasoning with Formal Language?
por: Jiang, Jin, et al.
Publicado: (2025)

Hidden You Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Logic Chain Injection
por: Wang, Zhilong, et al.
Publicado: (2024)

MetaLoRA: Tensor-Enhanced Adaptive Low-Rank Fine-tuning
por: Wang, Maolin, et al.
Publicado: (2025)

ERASE: Benchmarking Feature Selection Methods for Deep Recommender Systems
por: Jia, Pengyue, et al.
Publicado: (2024)

LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts
por: Xiao, Yijia, et al.
Publicado: (2024)

LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning
por: Jiang, Jin, et al.
Publicado: (2024)

Unraveling LLM Jailbreaks Through Safety Knowledge Neurons
por: Zhao, Chongwen, et al.
Publicado: (2025)

UniRank: Unified List-wise Reranking via Confidence-Ordered Denoising
por: Jia, Pengyue, et al.
Publicado: (2026)

On Cone Restriction Estimates in Higher Dimensions
por: Wang, Xiangyu
Publicado: (2024)

MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search
por: Zhang, Sheng, et al.
Publicado: (2026)

LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision
por: Xu, Jundong, et al.
Publicado: (2025)

Formal Logic Enabled Personalized Federated Learning Through Property Inference
por: An, Ziyan, et al.
Publicado: (2024)

Jailbreak Distillation: Renewable Safety Benchmarking
por: Zhang, Jingyu, et al.
Publicado: (2025)

LogicScan: An LLM-driven Framework for Detecting Business Logic Vulnerabilities in Smart Contracts
por: Gao, Jiaqi, et al.
Publicado: (2026)

Curriculum Learning for Efficient Chain-of-Thought Distillation via Structure-Aware Masking and GRPO
por: Yu, Bowen, et al.
Publicado: (2026)

A Generalized Hybrid Hoare Logic
por: Zhan, Naijun, et al.
Publicado: (2023)

Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification
por: Cao, Chuxue, et al.
Publicado: (2026)

GuardAD: Safeguarding Autonomous Driving MLLMs via Markovian Safety Logic
por: Zhang, Tianyuan, et al.
Publicado: (2026)

Scientific Logicality Enriched Methodology for LLM Reasoning: A Practice in Physics
por: Yu, Zhaoxin, et al.
Publicado: (2026)

GeoArena: Evaluating Open-World Geographic Reasoning in Large Vision-Language Models
por: Jia, Pengyue, et al.
Publicado: (2025)

Finite Variable Counting Logics with Restricted Requantification
por: Raßmann, Simon, et al.
Publicado: (2024)