Cover Image

SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Kaiwen, Zhao, Xuandong, Liu, Gaowen, Srinivasa, Jayanth, Feng, Aosong, Song, Dawn, Wang, Xin Eric
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMs
by: Liu, Yepeng, et al.
Published: (2025)

Improving LLM Safety Alignment with Dual-Objective Optimization
by: Zhao, Xuandong, et al.
Published: (2025)

Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs
by: Cai, Will, et al.
Published: (2025)

The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation
by: Xiong, Alexander, et al.
Published: (2025)

Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption
by: Liu, Yepeng, et al.
Published: (2025)

Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
by: Zhou, Tong, et al.
Published: (2024)

SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance
by: Huang, Caishuang, 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)

An Undetectable Watermark for Generative Image Models
by: Gunn, Sam, et al.
Published: (2024)

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

The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1
by: Zhou, Kaiwen, et al.
Published: (2025)

Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs
by: Zhao, Xuandong, et al.
Published: (2024)

Self-Sovereign Agent
by: Qu, Wenjie, et al.
Published: (2026)

GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis
by: Xie, Yueqi, et al.
Published: (2024)

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

SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning
by: Zhou, Kaiwen, et al.
Published: (2025)

Bag of Tricks for Subverting Reasoning-based Safety Guardrails
by: Chen, Shuo, et al.
Published: (2025)

MAGPIE: A benchmark for Multi-AGent contextual PrIvacy Evaluation
by: Juneja, Gurusha, et al.
Published: (2025)

Wrangling Entropy: Next-Generation Multi-Factor Key Derivation, Credential Hashing, and Credential Generation Functions
by: Roberts, Colin, et al.
Published: (2025)

SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts
by: Xin, Yuan, et al.
Published: (2026)

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

PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
by: Shen, Guobin, et al.
Published: (2025)

SafeFFI: Efficient Sanitization at the Boundary Between Safe and Unsafe Code in Rust and Mixed-Language Applications
by: Braunsdorf, Oliver, et al.
Published: (2025)

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

Multi-Trigger Poisoning Amplifies Backdoor Vulnerabilities in LLMs
by: Sivapiromrat, Sanhanat, et al.
Published: (2025)

PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety
by: Zhang, Zaibin, et al.
Published: (2024)

Signal in the Noise: Polysemantic Interference Transfers and Predicts Cross-Model Influence
by: Gong, Bofan, et al.
Published: (2025)

Understanding and Mitigating Over-refusal for Large Language Models via Safety Representation
by: Zhang, Junbo, et al.
Published: (2025)

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

RAG Safety: Exploring Knowledge Poisoning Attacks to Retrieval-Augmented Generation
by: Zhao, Tianzhe, et al.
Published: (2025)

MSWasm: Soundly Enforcing Memory-Safe Execution of Unsafe Code
by: Michael, Alexandra E., et al.
Published: (2022)

Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking
by: Gu, Tianle, et al.
Published: (2025)

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models
by: Zhao, Yunhan, et al.
Published: (2026)

ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs
by: Zhao, Gejian, et al.
Published: (2025)

Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models
by: Shen, Guobin, et al.
Published: (2024)

Analysing the Safety Pitfalls of Steering Vectors
by: Li, Yuxiao, et al.
Published: (2026)

WebSentinel: Detecting and Localizing Prompt Injection Attacks for Web Agents
by: Wang, Xilong, et al.
Published: (2026)

Safely Learning with Private Data: A Federated Learning Framework for Large Language Model
by: Zheng, JiaYing, et al.
Published: (2024)

Is Your Prompt Safe? Investigating Prompt Injection Attacks Against Open-Source LLMs
by: Wang, Jiawen, et al.
Published: (2025)

Navigation as Attackers Wish? Towards Building Robust Embodied Agents under Federated Learning
by: Zhang, Yunchao, et al.
Published: (2022)