Cover Image

What Matters For Safety Alignment?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Xing, Zhen, Hui-Ling, Yin, Lihao, Yu, Xianzhi, Dong, Zhenhua, Yuan, Mingxuan
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models
by: Zhang, Jinchuan, et al.
Published: (2025)

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

SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks
by: Li, Tianhao, et al.
Published: (2024)

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

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

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

Safety Alignment Should Be Made More Than Just A Few Attention Heads
by: Huang, Chao, et al.
Published: (2025)

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

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

From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment
by: Chae, Kyubyung, et al.
Published: (2025)

Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents
by: Nawal, Aditya, et al.
Published: (2026)

How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States
by: Zhou, Zhenhong, et al.
Published: (2024)

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
by: Xu, Chejian, et al.
Published: (2025)

Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs
by: Liu, Jinbo, 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)

Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region
by: Leong, Chak Tou, et al.
Published: (2025)

Lifelong Safety Alignment for Language Models
by: Wang, Haoyu, et al.
Published: (2025)

Superficial Safety Alignment Hypothesis
by: Li, Jianwei, et al.
Published: (2024)

Internal Safety Collapse in Frontier Large Language Models
by: Wu, Yutao, et al.
Published: (2026)

The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs
by: Liu, Songyang, et al.
Published: (2025)

Intent Laundering: AI Safety Datasets Are Not What They Seem
by: Golchin, Shahriar, et al.
Published: (2026)

Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation
by: Li, Xianzhi, et al.
Published: (2024)

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

What is in Your Safe Data? Identifying Benign Data that Breaks Safety
by: He, Luxi, et al.
Published: (2024)

MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
by: Gu, Tianle, et al.
Published: (2024)

Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
by: Yin, Qingyu, et al.
Published: (2025)

Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures
by: Su, Yanghao, et al.
Published: (2026)

An Independent Safety Evaluation of Kimi K2.5
by: Yong, Zheng-Xin, et al.
Published: (2026)

SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning
by: Zhou, Kaiwen, et al.
Published: (2025)

SGuard-v1: Safety Guardrail for Large Language Models
by: Lee, JoonHo, et al.
Published: (2025)

Proof-of-Guardrail in AI Agents and What (Not) to Trust from It
by: Jin, Xisen, et al.
Published: (2026)

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

Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings
by: Ying, Zonghao, et al.
Published: (2025)

SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models
by: Li, Lijun, et al.
Published: (2024)

Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs
by: Kim, Jinhwa, et al.
Published: (2025)

Bergeron: Combating Adversarial Attacks through a Conscience-Based Alignment Framework
by: Pisano, Matthew, et al.
Published: (2023)

Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments
by: Schnabl, Christoph, et al.
Published: (2025)

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

What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks
by: Kirch, Nathalie, et al.
Published: (2024)

What Was Your Prompt? A Remote Keylogging Attack on AI Assistants
by: Weiss, Roy, et al.
Published: (2024)