Cover Image

From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chae, Kyubyung, Jin, Hyunbin, Kim, Taesup
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

What If TSF: A Benchmark for Reframing Forecasting as Scenario-Guided Multimodal Forecasting
by: Jang, Jinkwan, et al.
Published: (2026)

Goal-guided Generative Prompt Injection Attack on Large Language Models
by: Zhang, Chong, et al.
Published: (2024)

Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment
by: Shao, Zedian, et al.
Published: (2024)

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

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

May I have your Attention? Breaking Fine-Tuning based Prompt Injection Defenses using Architecture-Aware Attacks
by: Pandya, Nishit V., et al.
Published: (2025)

Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents
by: Fujinuma, Yoshinari, et al.
Published: (2026)

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

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

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

Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models
by: Yi, Sibo, et al.
Published: (2025)

Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models
by: Belkhiter, Yannis, et al.
Published: (2026)

Claim-Guided Textual Backdoor Attack for Practical Applications
by: Song, Minkyoo, et al.
Published: (2024)

A Content-Based Framework for Cybersecurity Refusal Decisions in Large Language Models
by: Linder, Noa, et al.
Published: (2026)

Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
by: Hu, Xiaomeng, et al.
Published: (2024)

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
by: An, Hengyu, et al.
Published: (2025)

Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection
by: Hu, Xulin, et al.
Published: (2026)

Breaking PEFT Limitations: Leveraging Weak-to-Strong Knowledge Transfer for Backdoor Attacks in LLMs
by: Zhao, Shuai, et al.
Published: (2024)

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

Formalizing and Benchmarking Prompt Injection Attacks and Defenses
by: Liu, Yupei, et al.
Published: (2023)

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

An Investigation on Group Query Hallucination Attacks
by: Miao, Kehao, et al.
Published: (2025)

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

Can a Single Message Paralyze the AI Infrastructure? The Rise of AbO-DDoS Attacks through Targeted Mobius Injection
by: Liang, Zi, et al.
Published: (2026)

MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content
by: Guo, Ruoqi, et al.
Published: (2026)

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

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

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

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

From Threat Intelligence to Firewall Rules: Semantic Relations in Hybrid AI Agent and Expert System Architectures
by: Bonfanti, Chiara, et al.
Published: (2026)

AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models
by: Zhang, Jinchuan, 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)

Prompt Injection as Role Confusion
by: Ye, Charles, 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)

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

Resource Consumption Threats in Large Language Models
by: Zhang, Yuanhe, et al.
Published: (2026)

The Ethics of Interaction: Mitigating Security Threats in LLMs
by: Kumar, Ashutosh, et al.
Published: (2024)

DMFI: A Dual-Modality Log Analysis Framework for Insider Threat Detection with LoRA-Tuned Language Models
by: Kong, Kaichuan, et al.
Published: (2025)

Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information
by: Chae, Kyubyung, et al.
Published: (2024)