Cover Image

SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Caishuang, Zhao, Wanxu, Zheng, Rui, Lv, Huijie, Zhan, Wenyu, Dou, Shihan, Li, Sixian, Wang, Xiao, Zhou, Enyu, Ye, Junjie, Yang, Yuming, Gui, Tao, Zhang, Qi, Huang, Xuanjing
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models
by: Lv, Huijie, et al.
Published: (2024)

ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages
by: Ye, Junjie, et al.
Published: (2024)

ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios
by: Ye, Junjie, et al.
Published: (2024)

Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric
by: Yang, Yuming, et al.
Published: (2025)

MetaRM: Shifted Distributions Alignment via Meta-Learning
by: Dou, Shihan, et al.
Published: (2024)

RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning
by: Ye, Junjie, et al.
Published: (2024)

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning
by: Hua, Jiaqi, et al.
Published: (2025)

SafeAlign-VLA: A Negative-Enhanced Safe Alignment Framework for Risk-Aware Autonomous Driving
by: Tian, Kefei, et al.
Published: (2026)

Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective
by: Li, Tianlong, et al.
Published: (2024)

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

TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities
by: Zhang, Ming, et al.
Published: (2024)

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

StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback
by: Dou, Shihan, et al.
Published: (2024)

EVA: Editing for Versatile Alignment against Jailbreaks
by: Wang, Yi, et al.
Published: (2026)

RMB: Comprehensively Benchmarking Reward Models in LLM Alignment
by: Zhou, Enyu, et al.
Published: (2024)

VRPO: Rethinking Value Modeling for Robust RL Training under Noisy Supervision
by: Zhu, Dingwei, et al.
Published: (2025)

DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training
by: Zhu, Dingwei, et al.
Published: (2026)

Improving RL Exploration for LLM Reasoning through Retrospective Replay
by: Dou, Shihan, et al.
Published: (2025)

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

SafeBehavior: Simulating Human-Like Multistage Reasoning to Mitigate Jailbreak Attacks in Large Language Models
by: Zhao, Qinjian, et al.
Published: (2025)

Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition
by: Yang, Yuming, et al.
Published: (2024)

Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solution
by: Xu, Nuo, et al.
Published: (2024)

Steering LLMs via Scalable Interactive Oversight
by: Zhou, Enyu, et al.
Published: (2026)

GeneBreaker: Jailbreak Attacks against DNA Language Models with Pathogenicity Guidance
by: Zhang, Zaixi, et al.
Published: (2025)

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

Unlocking the Essence of Beauty: Advanced Aesthetic Reasoning with Relative-Absolute Policy Optimization
by: Liu, Boyang, et al.
Published: (2025)

FinToolSyn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval
by: Huang, Caishuang, et al.
Published: (2026)

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

DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training
by: Zhu, Dingwei, et al.
Published: (2025)

Untargeted Jailbreak Attack
by: Huang, Xinzhe, et al.
Published: (2025)

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

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval
by: Chen, Taiye, et al.
Published: (2025)

Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model
by: Wang, Siyin, et al.
Published: (2024)

InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance
by: Wang, Pengyu, et al.
Published: (2024)

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use
by: Ye, Junjie, et al.
Published: (2024)

JFTA-Bench: Evaluate LLM's Ability of Tracking and Analyzing Malfunctions Using Fault Trees
by: Wang, Yuhui, et al.
Published: (2026)

Effective Length Extrapolation via Dimension-Wise Positional Embeddings Manipulation
by: Lu, Yi, et al.
Published: (2025)

FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions
by: Li, Peng, et al.
Published: (2026)

60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering
by: Ye, Junjie, et al.
Published: (2024)

SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks
by: Li, Xiangman, et al.
Published: (2025)