Cover Image

Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience Replay

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Hao, Wang, Yanting, Li, Hao, Li, Rui, Sha, Lei
Format:	Preprint
Published:	2026
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

SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance
by: Huang, Caishuang, et al.
Published: (2024)

AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration
by: Zhou, Andy, et al.
Published: (2025)

Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks
by: Lu, Guoxin, et al.
Published: (2026)

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

EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models
by: Wu, Jialin, et al.
Published: (2025)

SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings
by: Lu, Weikai, et al.
Published: (2025)

LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs
by: Li, Ran, et al.
Published: (2025)

Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment
by: Wang, Haoran, et al.
Published: (2023)

ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack
by: Li, Hao, et al.
Published: (2026)

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment
by: Li, Hao, et al.
Published: (2025)

Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting
by: Chin, Zhi-Yi, et al.
Published: (2024)

Decoupled Alignment for Robust Plug-and-Play Adaptation
by: Luo, Haozheng, et al.
Published: (2024)

How Real is Your Jailbreak? Fine-grained Jailbreak Evaluation with Anchored Reference
by: Liu, Songyang, et al.
Published: (2026)

SAGE-RT: Synthetic Alignment data Generation for Safety Evaluation and Red Teaming
by: Kumar, Anurakt, et al.
Published: (2024)

Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training
by: Yong, Zheng-Xin, et al.
Published: (2025)

AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption
by: Wang, Yanting, et al.
Published: (2025)

What Matters For Safety Alignment?
by: Li, Xing, et al.
Published: (2026)

Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
by: Wang, Yanbo, et al.
Published: (2026)

Disabling Self-Correction in Retrieval-Augmented Generation via Stealthy Retriever Poisoning
by: Dai, Yanbo, et al.
Published: (2025)

Learning-Based Automated Adversarial Red-Teaming for Robustness Evaluation of Large Language Models
by: Wei, Zhang, et al.
Published: (2025)

Resource Consumption Red-Teaming for Large Vision-Language Models
by: Gao, Haoran, et al.
Published: (2025)

BAIT: Boundary-Guided Disclosure Escalation via Self-Conditioned Reasoning
by: Luo, Xuan, et al.
Published: (2026)

Self and Cross-Model Distillation for LLMs: Effective Methods for Refusal Pattern Alignment
by: Li, Jie, et al.
Published: (2024)

Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment
by: Wang, Kun, et al.
Published: (2026)

Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution
by: Zhang, Xiaozhe, et al.
Published: (2026)

RedTWIZ: Diverse LLM Red Teaming via Adaptive Attack Planning
by: Horal, Artur, et al.
Published: (2025)

From Essence to Defense: Adaptive Semantic-aware Watermarking for Embedding-as-a-Service Copyright Protection
by: Li, Hao, et al.
Published: (2025)

AJAR: Adaptive Jailbreak Architecture for Red-teaming
by: Dou, Yipu, et al.
Published: (2026)

SE#PCFG: Semantically Enhanced PCFG for Password Analysis and Cracking
by: Wang, Yangde, et al.
Published: (2023)

DualGuard: Dual-stream Large Language Model Watermarking Defense against Paraphrase and Spoofing Attack
by: Li, Hao, et al.
Published: (2025)

Safety Alignment Can Be Not Superficial With Explicit Safety Signals
by: Li, Jianwei, et al.
Published: (2025)

HauntAttack: When Attack Follows Reasoning as a Shadow
by: Ma, Jingyuan, et al.
Published: (2025)

Protecting Your LLMs with Information Bottleneck
by: Liu, Zichuan, et al.
Published: (2024)

S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models
by: Yuan, Xiaohan, et al.
Published: (2024)

Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory
by: Zhang, Ce, et al.
Published: (2026)

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
by: Wang, Zijun, et al.
Published: (2026)

GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models
by: Wang, Zilong, et al.
Published: (2025)

MOSAIC: Multi-Objective Slice-Aware Iterative Curation for Alignment
by: Dou, Yipu, et al.
Published: (2026)

Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety
by: Zhang, Yuyou, et al.
Published: (2025)

ProTransformer: Robustify Transformers via Plug-and-Play Paradigm
by: Hou, Zhichao, et al.
Published: (2024)