Cover Image

When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Guo, Jiahe, Guo, Xiangran, Hu, Yulin, Long, Zimo, Sui, Xingyu, Zhi, Xuda, Huang, Yongbo, He, Hao, Zhao, Weixiang, Zhao, Yanyan, Qin, Bing
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents
by: Hu, Yulin, et al.
Published: (2026)

TEA-Bench: A Systematic Benchmarking of Tool-enhanced Emotional Support Dialogue Agent
by: Sui, Xingyu, et al.
Published: (2026)

Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment
by: Zhao, Weixiang, et al.
Published: (2025)

Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities
by: Zhao, Weixiang, et al.
Published: (2025)

On Safety Risks in Experience-Driven Self-Evolving Agents
by: Zhao, Weixiang, et al.
Published: (2026)

Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction
by: Guo, Jiahe, et al.
Published: (2026)

Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs
by: Zhao, Weixiang, et al.
Published: (2025)

Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching
by: Zhao, Weixiang, et al.
Published: (2024)

Lens: Rethinking Multilingual Enhancement for Large Language Models
by: Zhao, Weixiang, et al.
Published: (2024)

When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
by: Zhao, Weixiang, et al.
Published: (2025)

Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement
by: Zhao, Weixiang, et al.
Published: (2025)

AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender
by: Zhao, Weixiang, et al.
Published: (2025)

Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter
by: Zhao, Weixiang, et al.
Published: (2025)

MPO: Multilingual Safety Alignment via Reward Gap Optimization
by: Zhao, Weixiang, et al.
Published: (2025)

Learning to Learn from Multimodal Experience
by: Sui, Xingyu, et al.
Published: (2026)

ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents
by: Fu, Xing, et al.
Published: (2026)

ConflictBench: Evaluating Human-AI Conflict via Interactive and Visually Grounded Environments
by: Zhao, Weixiang, et al.
Published: (2026)

Revealing Personality Traits: A New Benchmark Dataset for Explainable Personality Recognition on Dialogues
by: Sun, Lei, et al.
Published: (2024)

Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents
by: Su, Miao, et al.
Published: (2026)

Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence
by: Zhao, Weixiang, et al.
Published: (2024)

RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Models
by: Wang, Bichen, et al.
Published: (2024)

Large Language Model Agents Are Not Always Faithful Self-Evolvers
by: Zhao, Weixiang, et al.
Published: (2026)

SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models
by: Zhao, Weixiang, et al.
Published: (2024)

Text-Driven Emotionally Continuous Talking Face Generation
by: Yang, Hao, et al.
Published: (2026)

Rethinking Experience Utilization in Self-Evolving Language Model Agents
by: Zhao, Weixiang, et al.
Published: (2026)

STAR-S: Improving Safety Alignment through Self-Taught Reasoning on Safety Rules
by: Wu, Di, et al.
Published: (2026)

Semantics Over Syntax: Uncovering Pre-Authentication 5G Baseband Vulnerabilities
by: Huang, Qiqing, et al.
Published: (2026)

SafeScreen: A Safety-First Screening Framework for Personalized Video Retrieval for Vulnerable Users
by: Zhao, Wenzheng, et al.
Published: (2026)

Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models
by: Wu, Di, et al.
Published: (2024)

Exploring Personality-Aware Interactions in Salesperson Dialogue Agents
by: Cheng, Sijia, et al.
Published: (2025)

PSG-Agent: Personality-Aware Safety Guardrail for LLM-based Agents
by: Wu, Yaozu, et al.
Published: (2025)

In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents
by: Tan, Zhen, et al.
Published: (2025)

Fragile by Design: On the Limits of Adversarial Defenses in Personalized Generation
by: Chen, Zhen, et al.
Published: (2025)

UP-Person: Unified Parameter-Efficient Transfer Learning for Text-based Person Retrieval
by: Liu, Yating, et al.
Published: (2025)

Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment
by: Li, Yuxi, et al.
Published: (2024)

Hello Again! LLM-powered Personalized Agent for Long-term Dialogue
by: Li, Hao, et al.
Published: (2024)

Enhancing Personality Recognition in Dialogue by Data Augmentation and Heterogeneous Conversational Graph Networks
by: Fu, Yahui, et al.
Published: (2024)

When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output
by: Zhang, Shuoming, et al.
Published: (2025)

Reinforcement Learning for Personalized Dialogue Management
by: Hengst, Floris den, et al.
Published: (2019)

Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction
by: Huang, Zhaopei, et al.
Published: (2025)