Cover Image

May I have your Attention? Breaking Fine-Tuning based Prompt Injection Defenses using Architecture-Aware Attacks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pandya, Nishit V., Labunets, Andrey, Gao, Sicun, Fernandes, Earlence
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

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface
by: Labunets, Andrey, et al.
Published: (2025)

Systems Security Foundations for Agentic Computing
by: Christodorescu, Mihai, et al.
Published: (2025)

Agent Security is a Systems Problem
by: Christodorescu, Mihai, et al.
Published: (2026)

Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
by: Zhan, Qiusi, et al.
Published: (2025)

Defense Against Prompt Injection Attack by Leveraging Attack Techniques
by: Chen, Yulin, et al.
Published: (2024)

Checkpoint-GCG: Auditing and Attacking Fine-Tuning-Based Prompt Injection Defenses
by: Yang, Xiaoxue, et al.
Published: (2025)

Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods
by: Chen, Yulin, et al.
Published: (2025)

Breaking the Prompt Wall (I): A Real-World Case Study of Attacking ChatGPT via Lightweight Prompt Injection
by: Chang, Xiangyu, et al.
Published: (2025)

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs
by: Yeo, Andrew, et al.
Published: (2025)

A Critical Evaluation of Defenses against Prompt Injection Attacks
by: Jia, Yuqi, et al.
Published: (2025)

AegisAgent: An Autonomous Defense Agent Against Prompt Injection Attacks in LLM-HARs
by: Wang, Yihan, et al.
Published: (2025)

AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks
by: Jia, Yuqi, et al.
Published: (2026)

System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective
by: Wu, Fangzhou, et al.
Published: (2024)

Prompt Control-Flow Integrity: A Priority-Aware Runtime Defense Against Prompt Injection in LLM Systems
by: Alam, Md Takrim Ul, et al.
Published: (2026)

Early Approaches to Adversarial Fine-Tuning for Prompt Injection Defense: A 2022 Study of GPT-3 and Contemporary Models
by: Sandoval, Gustavo, et al.
Published: (2025)

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
by: Zhu, Kaijie, et al.
Published: (2025)

A Multi-Agent LLM Defense Pipeline Against Prompt Injection Attacks
by: Hossain, S M Asif, et al.
Published: (2025)

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

Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs
by: Zhong, Yinan, et al.
Published: (2025)

PromptShield: Deployable Detection for Prompt Injection Attacks
by: Jacob, Dennis, et al.
Published: (2025)

Defending Against Prompt Injection With a Few DefensiveTokens
by: Chen, Sizhe, et al.
Published: (2025)

FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks
by: Wang, Jiongxiao, et al.
Published: (2024)

ESLD (External Surrogate Latent Defense): A Latent-Space Architecture for Faster, Stronger Prompt-Injection Defense
by: Narendra, Yash
Published: (2026)

The Defense Trilemma: Why Prompt Injection Defense Wrappers Fail?
by: Bhatt, Manish, et al.
Published: (2026)

The Vulnerability of LLM Rankers to Prompt Injection Attacks
by: Yin, Yu, et al.
Published: (2026)

Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks
by: Kuo, Kevin, et al.
Published: (2026)

SUAD: Solid-Channel Ultrasound Injection Attack and Defense to Voice Assistants
by: Liu, Chao, et al.
Published: (2025)

AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
by: Debenedetti, Edoardo, et al.
Published: (2024)

PromptArmor: Simple yet Effective Prompt Injection Defenses
by: Shi, Tianneng, et al.
Published: (2025)

TopicAttack: An Indirect Prompt Injection Attack via Topic Transition
by: Chen, Yulin, et al.
Published: (2025)

Attention Tracker: Detecting Prompt Injection Attacks in LLMs
by: Hung, Kuo-Han, et al.
Published: (2024)

CASCADE: A Cascaded Hybrid Defense Architecture for Prompt Injection Detection in MCP-Based Systems
by: Turgut, İpek Abasıkeleş, et al.
Published: (2026)

Prompt Injection Attack to Tool Selection in LLM Agents
by: Shi, Jiawen, et al.
Published: (2025)

PINA: Prompt Injection Attack against Navigation Agents
by: Liu, Jiani, et al.
Published: (2026)

Can Indirect Prompt Injection Attacks Be Detected and Removed?
by: Chen, Yulin, et al.
Published: (2025)

Privacy in ERP Systems: Behavioral Models of Developers and Consultants
by: Pang, Alicia, et al.
Published: (2026)

Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks
by: Xiong, Chen, et al.
Published: (2024)

PromptLocate: Localizing Prompt Injection Attacks
by: Jia, Yuqi, et al.
Published: (2025)

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
by: Nasr, Milad, et al.
Published: (2025)

Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks
by: Xiang, Chong, et al.
Published: (2026)