Cover Image

DualEdit: Mitigating Safety Fallback in LLM Backdoor Editing via Affirmation-Refusal Regulation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Houcheng, Zhao, Zetong, Fang, Junfeng, Ma, Haokai, Wang, Ruipeng, Wang, Xiang, He, Xiangnan, Deng, Yang
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

AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models
by: Fang, Junfeng, et al.
Published: (2024)

DualEdit: Dual Editing for Knowledge Updating in Vision-Language Models
by: Shi, Zhiyi, et al.
Published: (2025)

AnyEdit: Edit Any Knowledge Encoded in Language Models
by: Jiang, Houcheng, et al.
Published: (2025)

We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems
by: Fang, Junfeng, et al.
Published: (2025)

Neuron-Level Sequential Editing for Large Language Models
by: Jiang, Houcheng, et al.
Published: (2024)

UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
by: Jiang, Houcheng, et al.
Published: (2026)

Contrastive Weak-to-strong Generalization
by: Jiang, Houcheng, et al.
Published: (2025)

NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels
by: Fang, Junfeng, et al.
Published: (2026)

Reinforced Lifelong Editing for Language Models
by: Li, Zherui, et al.
Published: (2025)

ACE: Concept Editing in Diffusion Models without Performance Degradation
by: Wang, Ruipeng, et al.
Published: (2025)

GuardAlign: Test-time Safety Alignment in Multimodal Large Language Models
by: Zhu, Xingyu, et al.
Published: (2026)

TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety
by: Hong, Zhepei, et al.
Published: (2026)

TrojanEdit: Multimodal Backdoor Attack Against Image Editing Model
by: Guo, Ji, et al.
Published: (2024)

Think Before Refusal : Triggering Safety Reflection in LLMs to Mitigate False Refusal Behavior
by: Si, Shengyun, et al.
Published: (2025)

SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models
by: Fang, Junfeng, et al.
Published: (2025)

Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation
by: Zhu, Xingyu, et al.
Published: (2026)

StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models
by: Bi, Baolong, et al.
Published: (2024)

ORFuzz: Fuzzing the "Other Side" of LLM Safety -- Testing Over-Refusal
by: Zhang, Haonan, et al.
Published: (2025)

SOD: Step-wise On-policy Distillation for Small Language Model Agents
by: Zhong, Qiyong, et al.
Published: (2026)

Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint
by: Du, Yanrui, et al.
Published: (2025)

Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment
by: Xue, Zhiyu, et al.
Published: (2026)

MDE-Edit: Masked Dual-Editing for Multi-Object Image Editing via Diffusion Models
by: Zhu, Hongyang, et al.
Published: (2025)

EfficientEdit: Accelerating Code Editing via Edit-Oriented Speculative Decoding
by: Wang, Peiding, et al.
Published: (2025)

Are We Evaluating the Edit Locality of LLM Model Editing Properly?
by: Liu, Wei, et al.
Published: (2026)

bi-GRPO: Bidirectional Optimization for Jailbreak Backdoor Injection on LLMs
by: Ji, Wence, et al.
Published: (2025)

Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems
by: Li, Zherui, et al.
Published: (2025)

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation
by: Zhu, Runchuan, et al.
Published: (2025)

TweezeEdit: Consistent and Efficient Image Editing with Path Regularization
by: Mao, Jianda, et al.
Published: (2025)

Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models
by: Wan, Guangnian, et al.
Published: (2026)

Learning to Edit: Aligning LLMs with Knowledge Editing
by: Jiang, Yuxin, et al.
Published: (2024)

ADS-Edit: A Multimodal Knowledge Editing Dataset for Autonomous Driving Systems
by: Wang, Chenxi, et al.
Published: (2025)

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
by: Yuan, Youliang, et al.
Published: (2024)

EditLord: Learning Code Transformation Rules for Code Editing
by: Li, Weichen, et al.
Published: (2025)

AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint
by: Sheng, Leheng, et al.
Published: (2025)

EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing
by: Zheng, Kaizhi, et al.
Published: (2024)

DiT4Edit: Diffusion Transformer for Image Editing
by: Feng, Kunyu, et al.
Published: (2024)

Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group Normalization
by: Li, Jinghan, et al.
Published: (2026)

EXGC: Bridging Efficiency and Explainability in Graph Condensation
by: Fang, Junfeng, et al.
Published: (2024)

Group Editing: Edit Multiple Images in One Go
by: Ma, Yue, et al.
Published: (2026)

Mitigating Backdoor Attacks using Activation-Guided Model Editing
by: Hsieh, Felix, et al.
Published: (2024)