English
Related papers

Related papers: QueryIPI: Query-agnostic Indirect Prompt Injection…

200 papers

The proliferation of text-to-image diffusion models (T2I DMs) has led to an increased presence of AI-generated images in daily life. However, biased T2I models can generate content with specific tendencies, potentially influencing people's…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Huayang Huang , Xiangye Jin , Jiaxu Miao , Yu Wu

Evolving AI systems increasingly deploy multi-agent architectures where autonomous agents collaborate, share information, and delegate tasks through developing protocols. This connectivity, while powerful, introduces novel security risks.…

Cryptography and Security · Computer Science 2025-07-30 Gauri Sharma , Vidhi Kulkarni , Miles King , Ken Huang

Large Language Model (LLM) agents are increasingly used to automate complex workflows, but integrating untrusted external data with privileged execution exposes them to severe security risks, particularly direct and indirect prompt…

Cryptography and Security · Computer Science 2026-04-28 Zonghao Ying , Haozheng Wang , Jiangfan Liu , Quanchen Zou , Aishan Liu , Jian Yang , Yaodong Yang , Xianglong Liu

Extremely large image generators offer significant transformative potential across diverse sectors. It allows users to design specific prompts to generate realistic images through some black-box APIs. However, some studies reveal that image…

Cryptography and Security · Computer Science 2024-02-26 Yu Tian , Xiao Yang , Yinpeng Dong , Heming Yang , Hang Su , Jun Zhu

Deep neural networks excel at comprehending complex visual signals, delivering on par or even superior performance to that of human experts. However, ad-hoc visual explanations of model decisions often reveal an alarming level of reliance…

Computer Vision and Pattern Recognition · Computer Science 2021-05-03 Dong Wang , Yuewei Yang , Chenyang Tao , Zhe Gan , Liqun Chen , Fanjie Kong , Ricardo Henao , Lawrence Carin

The prompt-based learning paradigm, which bridges the gap between pre-training and fine-tuning, achieves state-of-the-art performance on several NLP tasks, particularly in few-shot settings. Despite being widely applied, prompt-based…

Computation and Language · Computer Science 2024-02-05 Shuai Zhao , Jinming Wen , Luu Anh Tuan , Junbo Zhao , Jie Fu

Tool selection is a key component of LLM agents. A popular approach follows a two-step process - \emph{retrieval} and \emph{selection} - to pick the most appropriate tool from a tool library for a given task. In this work, we introduce…

Cryptography and Security · Computer Science 2025-08-26 Jiawen Shi , Zenghui Yuan , Guiyao Tie , Pan Zhou , Neil Zhenqiang Gong , Lichao Sun

Clarification-seeking behavior is widely regarded as a desirable property of LLM agents, enabling them to resolve ambiguity before acting on underspecified tasks. However, the security implications of this interaction pattern remain…

Cryptography and Security · Computer Science 2026-05-19 Udari Madhushani Sehwag , Zhengyang Shan , Heming Liu , Dileepa Lakshan , Joseph Brandifino , Max Fenkell

Current tool-using AI agents suffer from limited action space, context inefficiency, and probabilistic instability that makes them unsuitable for handling repetitive tasks which are otherwise reliably and efficiently tackled by agentic…

Software Engineering · Computer Science 2025-12-19 Nishant Gaurav , Adit Akarsh , Tejas Ravishankar , Manoj Bajaj

As Large Language Models (LLMs) grow increasingly powerful, multi-agent systems are becoming more prevalent in modern AI applications. Most safety research, however, has focused on vulnerabilities in single-agent LLMs. These include prompt…

Multiagent Systems · Computer Science 2024-10-11 Donghyun Lee , Mo Tiwari

Modern AI agents optimize programs by refactoring source code to trigger trusted compiler transformations. This preserves program semantics and reduces source code pollution, making the program easier to maintain and portable across…

Programming Languages · Computer Science 2026-04-16 Akash Deo , Simone Campanoni , Tommy McMichen

Deep neural networks (DNNs) are sensitive to adversarial data in a variety of scenarios, including the black-box scenario, where the attacker is only allowed to query the trained model and receive an output. Existing black-box methods for…

Computer Vision and Pattern Recognition · Computer Science 2022-11-29 Raz Lapid , Zvika Haramaty , Moshe Sipper

Web agents powered by vision-language models (VLMs) enable autonomous interaction with web environments by perceiving and acting on both visual and textual webpage content to accomplish user-specified tasks. However, they are highly…

Cryptography and Security · Computer Science 2026-04-15 Yulin Chen , Tri Cao , Haoran Li , Yue Liu , Yibo Li , Yufei He , Le Minh Khoi , Yangqiu Song , Shuicheng Yan , Bryan Hooi

Deep learning has made significant breakthroughs in many fields, including electroencephalogram (EEG) based brain-computer interfaces (BCIs). However, deep learning models are vulnerable to adversarial attacks, in which deliberately…

Machine Learning · Computer Science 2019-11-12 Xue Jiang , Xiao Zhang , Dongrui Wu

In the scope of "AI for Science", solving inverse problems is a longstanding challenge in materials and drug discovery, where the goal is to determine the hidden structures given a set of desirable properties. Deep generative models are…

Machine Learning · Computer Science 2022-12-05 Jiaxin Zhang , Sirui Bi , Victor Fung

When large language model (LLM) agents are increasingly deployed to automate tasks and interact with untrusted external data, prompt injection emerges as a significant security threat. By injecting malicious instructions into the data that…

Cryptography and Security · Computer Science 2026-02-05 Yizhu Wang , Sizhe Chen , Raghad Alkhudair , Basel Alomair , David Wagner

A prompt injection attack aims to inject malicious instruction/data into the input of an LLM-Integrated Application such that it produces results as an attacker desires. Existing works are limited to case studies. As a result, the…

Cryptography and Security · Computer Science 2025-11-13 Yupei Liu , Yuqi Jia , Runpeng Geng , Jinyuan Jia , Neil Zhenqiang Gong

Machine learning has been applied to a broad range of applications and some of them are available online as application programming interfaces (APIs) with either free (trial) or paid subscriptions. In this paper, we study adversarial…

Machine Learning · Computer Science 2018-11-06 Yi Shi , Yalin E. Sagduyu , Kemal Davaslioglu , Jason H. Li

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…

Cryptography and Security · Computer Science 2025-11-24 Yige Li , Zhe Li , Wei Zhao , Nay Myat Min , Hanxun Huang , Xingjun Ma , Jun Sun

Existing red-teaming studies on GUI agents have important limitations. Adversarial perturbations typically require white-box access, which is unavailable for commercial systems, while prompt injection is increasingly mitigated by stronger…

Cryptography and Security · Computer Science 2026-04-10 Wenkui Yang , Chao Jin , Haisu Zhu , Weilin Luo , Derek Yuen , Kun Shao , Huaibo Huang , Junxian Duan , Jie Cao , Ran He