English
Related papers

Related papers: CommandSans: Securing AI Agents with Surgical Prec…

200 papers

Recent advances in diffusion models have notably enhanced text-to-image (T2I) generation quality, but they also raise the risk of generating unsafe content. Traditional safety methods like text blacklisting or harmful content classification…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Zongsheng Cao , Yangfan He , Anran Liu , Jun Xie , Feng Chen , Zepeng Wang

Defenses against indirect prompt injection (IPI) in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been…

Cryptography and Security · Computer Science 2026-05-13 Yassin H. Rassul , Tarik A. Rashid

Adversarial images pose a severe security threat to multimodal large language models through prompt injection. Existing defenses largely lack a principled understanding of the underlying mechanisms and struggle to balance efficiency and…

Machine Learning · Computer Science 2026-05-26 Dongpeng Zhang , Ke Ma , Yangbangyan Jiang , Gaozheng Pei , Longtao Huang , Qianqian Xu , Qingming Huang

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

Machine Learning · Computer Science 2025-10-08 Zizhao Wang , Dingcheng Li , Vaishakh Keshava , Phillip Wallis , Ananth Balashankar , Peter Stone , Lukas Rutishauser

Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone…

Cryptography and Security · Computer Science 2026-05-08 Javad Forough , Marios Kogias , Hamed Haddadi

LLM agents are increasingly deployed to automate real-world tasks by invoking APIs through natural language instructions. While powerful, they often suffer from misinterpretation of user intent, leading to the agent's actions that diverge…

Software Engineering · Computer Science 2025-10-27 Shiwei Feng , Xiangzhe Xu , Xuan Chen , Kaiyuan Zhang , Syed Yusuf Ahmed , Zian Su , Mingwei Zheng , Xiangyu Zhang

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 comprehensive…

Cryptography and Security · Computer Science 2025-11-21 Badrinath Ramakrishnan , Akshaya Balaji

Intrusion detection is a long standing and crucial problem in security. A system capable of detecting intrusions automatically is on great demand in enterprise security solutions. Existing solutions rely heavily on hand-crafted rules…

Cryptography and Security · Computer Science 2024-04-23 Jiongliang Lin , Yiwen Guo , Hao Chen

This paper presents a novel approach to evaluating the security of large language models (LLMs) against prompt leakage-the exposure of system-level prompts or proprietary configurations. We define prompt leakage as a critical threat to…

Cryptography and Security · Computer Science 2025-02-19 Tvrtko Sternak , Davor Runje , Dorian Granoša , Chi Wang

Previous research on testing the vulnerabilities in Large Language Models (LLMs) using adversarial attacks has primarily focused on nonsensical prompt injections, which are easily detected upon manual or automated review (e.g., via byte…

Computation and Language · Computer Science 2024-07-29 Nilanjana Das , Edward Raff , Manas Gaur

Safety-oriented instruction-following is supposed to keep LLM-controlled robots safe. We show it also creates an availability attack surface. By injecting short safety-plausible phrases (1-5 tokens) into a robots audio channel, an adversary…

Cryptography and Security · Computer Science 2026-04-29 Jonathan Steinberg , Oren Gal

As AI agents automate critical workloads, they remain vulnerable to indirect prompt injection (IPI) attacks. Current defenses rely on monitoring protocols that jointly evaluate an agent's Chain-of-Thought (CoT) and tool-use actions to…

Cryptography and Security · Computer Science 2026-02-26 Jafar Isbarov , Murat Kantarcioglu

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks,…

Computation and Language · Computer Science 2024-11-11 Md Abdur Rahman , Fan Wu , Alfredo Cuzzocrea , Sheikh Iqbal Ahamed

LLM-powered agents often use prompt compression to reduce inference costs, but this introduces a new security risk. Compression modules, which are optimized for efficiency rather than safety, can be manipulated by adversarial inputs,…

Cryptography and Security · Computer Science 2025-11-18 Zesen Liu , Zhixiang Zhang , Yuchong Xie , Dongdong She

Prompt injection attacks aim to contaminate the input data of an LLM to mislead it into completing an attacker-chosen task instead of the intended task. In many applications and agents, the input data originates from multiple sources, with…

Cryptography and Security · Computer Science 2025-12-16 Reachal Wang , Yuqi Jia , Neil Zhenqiang Gong

Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and commercial concern. Existing safety evaluations predominantly rely on fixed collections of…

Computation and Language · Computer Science 2026-03-23 Zafir Shamsi , Nikhil Chekuru , Zachary Guzman , Shivank Garg

Sensor systems are extremely popular today and vulnerable to sensor data attacks. Due to possible devastating consequences, counteracting sensor data attacks is an extremely important topic, which has not seen sufficient study. This paper…

Cryptography and Security · Computer Science 2026-01-07 Xubin Fang , Rick S. Blum , Ramesh Bharadwaj , Brian M. Sadler

Prompt injection attacks can compromise the security and stability of critical systems, from infrastructure to large web applications. This work curates and augments a prompt injection dataset based on the HackAPrompt Playground Submissions…

Cryptography and Security · Computer Science 2025-12-16 Safwan Shaheer , G. M. Refatul Islam , Mohammad Rafid Hamid , Md. Abrar Faiaz Khan , Md. Omar Faruk , Yaseen Nur

Prompt injection attacks, where malicious input is designed to manipulate AI systems into ignoring their original instructions and following unauthorized commands instead, were first discovered by Preamble, Inc. in May 2022 and responsibly…

Cryptography and Security · Computer Science 2025-07-18 Jeremy McHugh , Kristina Šekrst , Jon Cefalu

When AI agents retrieve and reason over external documents, adversaries can manipulate the data they receive to subvert their behaviour. Previous research has studied indirect prompt injection, where the attacker injects malicious…

Computation and Language · Computer Science 2025-10-14 Michael Schlichtkrull