English
Related papers

Related papers: PromptLocate: Localizing Prompt Injection Attacks

200 papers

Large language models (LLMs) have shown remarkable performance on many different Natural Language Processing (NLP) tasks. Prompt engineering plays a key role in adding more to the already existing abilities of LLMs to achieve significant…

Computation and Language · Computer Science 2024-07-25 Shubham Vatsal , Harsh Dubey

Indirect prompt injection attacks (IPIAs), where large language models (LLMs) follow malicious instructions hidden in input data, pose a critical threat to LLM-powered agents. In this paper, we present IntentGuard, a general defense…

Cryptography and Security · Computer Science 2025-12-02 Mintong Kang , Chong Xiang , Sanjay Kariyappa , Chaowei Xiao , Bo Li , Edward Suh

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

Despite excellent average-case performance of many image classifiers, their performance can substantially deteriorate on semantically coherent subgroups of the data that were under-represented in the training data. These systematic errors…

Computer Vision and Pattern Recognition · Computer Science 2023-04-13 Jan Hendrik Metzen , Robin Hutmacher , N. Grace Hua , Valentyn Boreiko , Dan Zhang

Prompt engineering is an essential technique for enhancing the abilities of large language models (LLMs) by providing explicit and specific instructions. It enables LLMs to excel in various tasks, such as arithmetic reasoning, question…

Computation and Language · Computer Science 2024-03-29 Fobo Shi , Peijun Qing , Dong Yang , Nan Wang , Youbo Lei , Haonan Lu , Xiaodong Lin , Duantengchuan Li

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

The tidal wave of advancements in Large Language Models (LLMs) has led to their swift integration into application-level logic. Many software systems now use prompts to interact with these black-box models, combining natural language with…

Software Engineering · Computer Science 2025-01-23 Dhia Elhaq Rzig , Dhruba Jyoti Paul , Kaiser Pister , Jordan Henkel , Foyzul Hassan

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

Automated log analysis is crucial in modern software-intensive systems for facilitating program comprehension throughout software maintenance and engineering life cycles. Existing methods perform tasks such as log parsing and log anomaly…

Software Engineering · Computer Science 2024-01-29 Yilun Liu , Shimin Tao , Weibin Meng , Jingyu Wang , Wenbing Ma , Yanqing Zhao , Yuhang Chen , Hao Yang , Yanfei Jiang , Xun Chen

Large foundation models, known for their strong zero-shot generalization, have excelled in visual and language applications. However, applying them to medical image segmentation, a domain with diverse imaging types and target labels,…

Image and Video Processing · Electrical Eng. & Systems 2024-04-18 Junde Wu , Jiayuan Zhu , Yueming Jin , Min Xu

In adversarial machine learning, new defenses against attacks on deep learning systems are routinely broken soon after their release by more powerful attacks. In this context, forensic tools can offer a valuable complement to existing…

Cryptography and Security · Computer Science 2022-06-17 Shawn Shan , Arjun Nitin Bhagoji , Haitao Zheng , Ben Y. Zhao

With the increase in software vulnerabilities that cause significant economic and social losses, automatic vulnerability detection has become essential in software development and maintenance. Recently, large language models (LLMs) like GPT…

Software Engineering · Computer Science 2024-04-15 Chenyuan Zhang , Hao Liu , Jiutian Zeng , Kejing Yang , Yuhong Li , Hui Li

Large language models (LLMs) can be used as accessible and intelligent chatbots by constructing natural language queries and directly inputting the prompt into the large language model. However, different prompt' constructions often lead to…

Computation and Language · Computer Science 2023-12-14 Jinta Weng , Jiarui Zhang , Yue Hu , Daidong Fa , Xiaofeng Xuand , Heyan Huang

Large language models (LLMs) are increasingly used in interactive and retrieval-augmented systems, but they remain vulnerable to prompt injection attacks, where injected secondary prompts force the model to deviate from the user's…

Cryptography and Security · Computer Science 2026-04-02 Md Jahedur Rahman , Ihsen Alouani

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

Directed fuzzing aims to find program inputs that lead to specified target program states. It has broad applications, such as debugging system crashes, confirming reported bugs, and generating exploits for potential vulnerabilities. This…

Cryptography and Security · Computer Science 2025-12-10 Jie Zhu , Chihao Shen , Ziyang Li , Jiahao Yu , Yizheng Chen , Kexin Pei

Providing timely and personalized guidance for students' programming assignments, offers significant practical value for helping students complete assignments and enhance their learning. In recent years, various automated Fault Localization…

Software Engineering · Computer Science 2025-10-01 Fang Liu , Tianze Wang , Li Zhang , Zheyu Yang , Jing Jiang , Zian Sun

In this work, we demonstrate that certain machine unlearning methods may fail under straightforward prompt attacks. We systematically evaluate eight unlearning techniques across three model families using output-based, logit-based, and…

Cryptography and Security · Computer Science 2025-08-15 Yeonwoo Jang , Shariqah Hossain , Ashwin Sreevatsa , Diogo Cruz

System prompt configuration can make the difference between near-total phishing blindness and near-perfect detection in LLM email agents. We present PhishNChips, a study of 11 models under 10 prompt strategies, showing that prompt-model…

Cryptography and Security · Computer Science 2026-03-27 Ron Litvak

Accurate segmentation of lesions in longitudinal whole-body CT is essential for monitoring disease progression and treatment response. While automated methods benefit from incorporating longitudinal information, they remain limited in their…

Image and Video Processing · Electrical Eng. & Systems 2025-09-03 Yannick Kirchhoff , Maximilian Rokuss , Fabian Isensee , Klaus H. Maier-Hein
‹ Prev 1 8 9 10 Next ›