Cover Image

Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Yinzhi, Wang, Ming, Feng, Shi, Yang, Xiaocui, Wang, Daling, Zhang, Yifei
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
by: Xu, Zhangchen, et al.
Published: (2024)

Language Models as Continuous Self-Evolving Data Engineers
by: Wang, Peidong, et al.
Published: (2024)

Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering
by: Zhang, Xiaoming, et al.
Published: (2024)

Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation
by: Shangguan, Haonan, et al.
Published: (2025)

Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks
by: Zhao, Jiawei, et al.
Published: (2024)

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

RoCar: A Relationship Network-based Evaluation Method for Large Language Models
by: Wang, Ming, et al.
Published: (2023)

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
by: Liu, Fan, et al.
Published: (2024)

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
by: Zhou, Andy, et al.
Published: (2024)

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
by: Jiang, Tanqiu, et al.
Published: (2024)

AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulation
by: Wang, Ming, et al.
Published: (2025)

CIRAG: Construction-Integration Retrieval and Adaptive Generation for Multi-hop Question Answering
by: Wei, Zili, et al.
Published: (2026)

Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing
by: Zhao, Wei, et al.
Published: (2024)

Generative Emotion Cause Explanation in Multimodal Conversations
by: Wang, Lin, et al.
Published: (2024)

MTRouter: Cost-Aware Multi-Turn LLM Routing with History-Model Joint Embeddings
by: Zhang, Yiqun, et al.
Published: (2026)

Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring
by: Mu, Honglin, et al.
Published: (2024)

Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models
by: Yi, Jingwei, et al.
Published: (2023)

GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testing
by: Wang, Ming, et al.
Published: (2026)

Jailbreaking Safeguarded Text-to-Image Models via Large Language Models
by: Jiang, Zhengyuan, et al.
Published: (2025)

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
by: Robey, Alexander, et al.
Published: (2023)

Defending against Jailbreak through Early Exit Generation of Large Language Models
by: Zhao, Chongwen, et al.
Published: (2024)

Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models
by: Xu, Zihao, et al.
Published: (2024)

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)

From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning
by: Wang, Xiao, et al.
Published: (2026)

Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models
by: Tu, Shangqing, et al.
Published: (2024)

Audio Jailbreaks in Large Audio-Language Models: Taxonomy, Attack-Defense Analysis, and Cost-Aware Evaluation
by: Feng, Bo-Han, et al.
Published: (2026)

Jailbreak Attacks and Defenses Against Large Language Models: A Survey
by: Yi, Sibo, et al.
Published: (2024)

JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models
by: Ran, Delong, et al.
Published: (2024)

Distract Large Language Models for Automatic Jailbreak Attack
by: Xiao, Zeguan, et al.
Published: (2024)

Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
by: Zhang, Zhexin, et al.
Published: (2023)

Steering Multimodal Large Language Models Decoding for Context-Aware Safety
by: Liu, Zheyuan, et al.
Published: (2025)

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models
by: Yu, Miao, et al.
Published: (2024)

LastingBench: Defend Benchmarks Against Knowledge Leakage
by: Fang, Yixiong, et al.
Published: (2025)

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

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

MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots
by: Wang, Yuhao, et al.
Published: (2026)

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
by: Zhao, Shiji, et al.
Published: (2025)

LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models
by: Lin, Shi, et al.
Published: (2024)

Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles
by: Sun, Xiongtao, et al.
Published: (2024)

Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks
by: Zhou, Yue, et al.
Published: (2024)