Cover Image

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yi, Zhang, An, Zhang, XiuYu, Sheng, Leheng, Chen, Yuxin, Liang, Zhenkai, Wang, Xiang
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

VisuoAlign: Safety Alignment of LVLMs with Multimodal Tree Search
by: Li, MingSheng, et al.
Published: (2025)

Agent Safety Alignment via Reinforcement Learning
by: Sha, Zeyang, et al.
Published: (2025)

Research on CNN-BiLSTM Network Traffic Anomaly Detection Model Based on MindSpore
by: Xiang, Qiuyan, et al.
Published: (2025)

Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs
by: Ferrand, Jean-Charles Noirot, et al.
Published: (2025)

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

aiXamine: Simplified LLM Safety and Security
by: Deniz, Fatih, et al.
Published: (2025)

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

SafeThinker: Reasoning about Risk to Deepen Safety Beyond Shallow Alignment
by: Fang, Xianya, et al.
Published: (2026)

Reimagining Safety Alignment with An Image
by: Xia, Yifan, et al.
Published: (2025)

Safety Layers in Aligned Large Language Models: The Key to LLM Security
by: Li, Shen, et al.
Published: (2024)

MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming
by: Guo, Weiyang, et al.
Published: (2025)

Robustifying Safety-Aligned Large Language Models through Clean Data Curation
by: Liu, Xiaoqun, et al.
Published: (2024)

Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense
by: Zhang, Jiawen, et al.
Published: (2025)

OptiLeak: Efficient Prompt Reconstruction via Reinforcement Learning in Multi-tenant LLM Services
by: Wang, Longxiang, et al.
Published: (2026)

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety
by: Wang, Kun, et al.
Published: (2026)

Governable AI: Provable Safety Under Extreme Threat Models
by: Wang, Donglin, et al.
Published: (2025)

Why Do Aligned LLMs Remain Jailbreakable: Refusal-Escape Directions, Operator-Level Sources, and Safety-Utility Trade-off
by: Chen, Yu, et al.
Published: (2026)

State-Dependent Safety Failures in Multi-Turn Language Model Interaction
by: Li, Pengcheng, 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)

PiMRef: Detecting and Explaining Ever-evolving Spear Phishing Emails with Knowledge Base Invariants
by: Liu, Ruofan, et al.
Published: (2025)

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

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

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

AttackSeqBench: Benchmarking the Capabilities of LLMs for Attack Sequences Understanding
by: Ma, Haokai, et al.
Published: (2025)

MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation
by: Yan, Lu, et al.
Published: (2025)

Adversarial Attack-Defense Co-Evolution for LLM Safety Alignment via Tree-Group Dual-Aware Search and Optimization
by: Li, Xurui, et al.
Published: (2025)

Measuring Safety Alignment Effects in Autonomous Security Agents
by: David, Isaac, et al.
Published: (2026)

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

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis
by: Xu, Zhenhao, et al.
Published: (2026)

A Novel and Practical Universal Adversarial Perturbations against Deep Reinforcement Learning based Intrusion Detection Systems
by: Zhang, H., et al.
Published: (2025)

FreakOut-LLM: The Effect of Emotional Stimuli on Safety Alignment
by: Kuznetsov, Daniel, et al.
Published: (2026)

MASKDROID: Robust Android Malware Detection with Masked Graph Representations
by: Zheng, Jingnan, et al.
Published: (2024)

SoSBench: Benchmarking Safety Alignment on Six Scientific Domains
by: Jiang, Fengqing, et al.
Published: (2025)

RASA: Routing-Aware Safety Alignment for Mixture-of-Experts Models
by: Liang, Jiacheng, et al.
Published: (2026)

Zero-Knowledge Federated Learning: A New Trustworthy and Privacy-Preserving Distributed Learning Paradigm
by: Wang, Taotao, et al.
Published: (2025)

SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models
by: Chen, Yulong, et al.
Published: (2025)

Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications
by: David, Isaac, et al.
Published: (2026)

Matching Ranks Over Probability Yields Truly Deep Safety Alignment
by: Vega, Jason, et al.
Published: (2025)

Defensive Refusal Bias: How Safety Alignment Fails Cyber Defenders
by: Campbell, David, et al.
Published: (2026)