English
Related papers

Related papers: SnapGuard: Lightweight Prompt Injection Detection …

200 papers

Logic locking is a prominent technique to protect the integrity of hardware designs throughout the integrated circuit design and fabrication flow. However, in recent years, the security of locking schemes has been thoroughly challenged by…

Cryptography and Security · Computer Science 2021-05-20 Dominik Sisejkovic , Farhad Merchant , Lennart M. Reimann , Harshit Srivastava , Ahmed Hallawa , Rainer Leupers

Autonomous UI agents powered by AI have tremendous potential to boost human productivity by automating routine tasks such as filing taxes and paying bills. However, a major challenge in unlocking their full potential is security, which is…

Cryptography and Security · Computer Science 2025-05-20 Ivan Evtimov , Arman Zharmagambetov , Aaron Grattafiori , Chuan Guo , Kamalika Chaudhuri

Inspired by the success of large language models (LLMs), there is a significant research shift from traditional graph learning methods to LLM-based graph frameworks, formally known as GraphLLMs. GraphLLMs leverage the reasoning power of…

Machine Learning · Computer Science 2025-06-16 Qihai Zhang , Xinyue Sheng , Yuanfu Sun , Qiaoyu Tan

An emerging family of language models (LMs), capable of processing both text and images within a single visual view, has the promise to unlock complex tasks such as chart understanding and UI navigation. We refer to these models as…

Computation and Language · Computer Science 2024-02-27 Tianyu Gao , Zirui Wang , Adithya Bhaskar , Danqi Chen

LLM agents are widely used as agents for customer support, content generation, and code assistance. However, they are vulnerable to prompt injection attacks, where adversarial inputs manipulate the model's behavior. Traditional defenses…

Cryptography and Security · Computer Science 2025-06-09 Zhilong Wang , Neha Nagaraja , Lan Zhang , Hayretdin Bahsi , Pawan Patil , Peng Liu

A Large Language Model (LLM) powered GUI agent is a specialized autonomous system that performs tasks on the user's behalf according to high-level instructions. It does so by perceiving and interpreting the graphical user interfaces (GUIs)…

Accurate rejection of sensitive or harmful visual content, i.e., harmful image guardrail, is critical in many application scenarios. This task must continuously adapt to the evolving safety policies and content across various domains and…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Caiyong Piao , Zhiyuan Yan , Haoming Xu , Yunzhen Zhao , Kaiqing Lin , Feiyang Xu , Shuigeng Zhou

Large language model (LLM) agents now execute long, tool-using tasks where final outcome checks can arrive too late for intervention. Online warning requires lightweight prefix monitors over heterogeneous traces, but hand-authored event…

Artificial Intelligence · Computer Science 2026-05-08 Xinmiao Huang , Jinwei Hu , Rajarshi Roy , Changshun Wu , Yi Dong , Xiaowei Huang

Recent work has embodied LLMs as agents, allowing them to access tools, perform actions, and interact with external content (e.g., emails or websites). However, external content introduces the risk of indirect prompt injection (IPI)…

Computation and Language · Computer Science 2024-08-06 Qiusi Zhan , Zhixiang Liang , Zifan Ying , Daniel Kang

Hidden LLM prompts have appeared in online documents with increasing frequency. Their goal is to trigger indirect prompt injection attacks while remaining undetected from human oversight, to manipulate LLM-powered automated document…

Cryptography and Security · Computer Science 2025-10-24 Toby Murray

The rise of large language models (LLMs) has enabled the generation of highly persuasive spam reviews that closely mimic human writing. These reviews pose significant challenges for existing detection systems and threaten the credibility of…

Computation and Language · Computer Science 2026-04-21 Xin Liu , Rongwu Xu , Xinyi Jia , Jason Liao , Jiao Sun , Ling Huang , Wei Xu

Prompt injection attacks manipulate large language models (LLMs) by misleading them to deviate from the original input instructions and execute maliciously injected instructions, because of their instruction-following capabilities and…

Cryptography and Security · Computer Science 2025-10-07 Yulin Chen , Haoran Li , Yuan Sui , Yufei He , Yue Liu , Yangqiu Song , Bryan Hooi

Large Language Model (LLM) agents increasingly operate across domains such as robotics, virtual assistants, and web automation. However, their stochastic decision-making introduces safety risks that are difficult to anticipate during…

Artificial Intelligence · Computer Science 2026-03-30 Haoyu Wang , Christopher M. Poskitt , Jiali Wei , Jun Sun

The critical challenge of prompt injection attacks in Large Language Models (LLMs) integrated applications, a growing concern in the Artificial Intelligence (AI) field. Such attacks, which manipulate LLMs through natural language inputs,…

Cryptography and Security · Computer Science 2024-01-17 Xuchen Suo

Recent developments in text-to-image models, particularly Stable Diffusion, have marked significant achievements in various applications. With these advancements, there are growing safety concerns about the vulnerability of the model that…

Computer Vision and Pattern Recognition · Computer Science 2024-01-18 Chenyu Zhang , Lanjun Wang , Anan Liu

As large language models (LLMs) advance, ensuring AI safety and alignment is paramount. One popular approach is prompt guards, lightweight mechanisms designed to filter malicious queries while being easy to implement and update. In this…

Machine Learning · Computer Science 2025-10-08 Jaiden Fairoze , Sanjam Garg , Keewoo Lee , Mingyuan Wang

Guardrail models (a.k.a. safety checkers) are widely deployed to screen user inputs before they reach large language models (LLMs), serving as a primary defense against prompt injection attacks. Due to strict context constraints, these…

Cryptography and Security · Computer Science 2026-05-25 Yuanbo Zhou , Changjia Zhu , Junyu Wang , Xu He , Yan Zhai , Kun Sun , Mingkui Wei , Junjie Xiong

This paper investigates the resilience of a ResNet-50 image classification model under two prominent security threats: Fast Gradient Sign Method (FGSM) adversarial attacks and malicious payload injection. Initially, the model attains a…

Cryptography and Security · Computer Science 2025-01-22 Umesh Yadav , Suman Niroula , Gaurav Kumar Gupta , Bicky Yadav

Prompt injection attacks pose a pervasive threat to the security of Large Language Models (LLMs). State-of-the-art prevention-based defenses typically rely on fine-tuning an LLM to enhance its security, but they achieve limited…

Cryptography and Security · Computer Science 2025-11-17 Yupei Liu , Yanting Wang , Yuqi Jia , Jinyuan Jia , Neil Zhenqiang Gong

Text-to-image generative models are widely deployed in creative tools and online platforms. To mitigate misuse, these systems rely on safety filters and moderation pipelines that aim to block harmful or policy violating content. In this…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Ahmed B Mustafa , Zihan Ye , Yang Lu , Michael P Pound , Shreyank N Gowda
‹ Prev 1 4 5 6 7 8 10 Next ›