paper-with-me

홈 › Papers

Design Patterns for Securing LLM Agents against Prompt Injections

2025-06-10 · Luca Beurer-Kellner, Beat Buesser Ana-Maria Creţu, Edoardo Debenedetti, Daniel Dobos, Daniel Fabian, Marc Fischer, David Froelicher, Kathrin Grosse, Daniel Naeff, Ezinwanne Ozoani, Andrew Paverd, Florian Tramèr, Václav Volhejn

As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing threats are prompt injection attacks, which exploit the agent's resilience on natural language inputs -- an especially dangerous threat when agents are granted tool access or handle sensitive information. In this work, we propose a set of principled design patterns for building AI agents with provable resistance to prompt injection. We systematically analyze these patterns, discuss their trade-offs in terms of utility and security, and illustrate their real-world applicability through a series of case studies.

📄 PDF Abstract BibTeX arXiv:2506.08837

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

The Cognitive Firewall:Securing Browser Based AI Agents Against Indirect Prompt Injection Via Hybrid Edge Cloud Defense

2026-03-24 · Qianlong Lan, Anuj Kaul arxiv

Deploying large language models (LLMs) as autonomous browser agents exposes a significant attack surface in the form of Indirect Prompt Injection (IPI). Cloud-based defenses can provide strong semantic analysis, but they…

Securing AI Agents with Information-Flow Control

2025-05-29 · Manuel Costa, Boris Köpf, Aashish Kolluri, Andrew Paverd 외

As AI agents become increasingly autonomous and capable, ensuring their security against vulnerabilities such as prompt injection becomes critical. This paper explores the use of information-flow control (IFC) to provide…

Securing AI Agents Against Prompt Injection Attacks

2025-11-19 · Badrinath Ramakrishnan, Akshaya Balaji arxiv

Retrieval-augmented generation (RAG) systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a…

Anomaly Detection

DECEPTICON: How Dark Patterns Manipulate Web Agents

2025-12-28 · Phil Cuvin, Hao Zhu, Diyi Yang arxiv

Deceptive UI designs, widely instantiated across the web and commonly known as dark patterns, manipulate users into performing actions misaligned with their goals. In this paper, we show that dark patterns are highly eff…

Self and Cross-Model Distillation for LLMs: Effective Methods for Refusal Pattern Alignment

2024-06-17 · Jie Li, Yi Liu, Chongyang Liu, Xiaoning Ren 외

Large Language Models (LLMs) like OpenAI's GPT series, Anthropic's Claude, and Meta's LLaMa have shown remarkable capabilities in text generation. However, their susceptibility to toxic prompts presents significant secur…

Text Generation