English
Related papers

Related papers: Knowledge Return Oriented Prompting (KROP)

200 papers

Large Language Models (LLMs) are vulnerable to prompt injection attacks, and several defenses have recently been proposed, often claiming to mitigate these attacks successfully. However, we argue that existing studies lack a principled…

Cryptography and Security · Computer Science 2025-05-27 Yuqi Jia , Zedian Shao , Yupei Liu , Jinyuan Jia , Dawn Song , Neil Zhenqiang Gong

The security of Large Language Model (LLM) applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are embedded within user inputs. Conventional defenses, which…

Cryptography and Security · Computer Science 2025-10-15 Dominik Schwarz

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

Knowledge erasure in large language models (LLMs) is important for ensuring compliance with data and AI regulations, safeguarding user privacy, mitigating bias, and misinformation. Existing unlearning methods aim to make the process of…

Cryptography and Security · Computer Science 2025-06-24 Yash Sinha , Manit Baser , Murari Mandal , Dinil Mon Divakaran , Mohan Kankanhalli

Safety, security, and compliance are essential requirements when aligning large language models (LLMs). However, many seemingly aligned LLMs are soon shown to be susceptible to jailbreak attacks. These attacks aim to circumvent the models'…

Cryptography and Security · Computer Science 2025-06-05 Chen Xiong , Xiangyu Qi , Pin-Yu Chen , Tsung-Yi Ho

State-of-the-art large language models (LLMs) are typically deployed as online services, requiring users to transmit detailed prompts to cloud servers. This raises significant privacy concerns. In response, we introduce ConfusionPrompt, a…

Cryptography and Security · Computer Science 2026-04-09 Peihua Mai , Youjia Yang , Ran Yan , Rui Ye , Yan Pang

As large language models (LLMs) grow more capable, concerns about their safe deployment have also grown. Although alignment mechanisms have been introduced to deter misuse, they remain vulnerable to carefully designed adversarial prompts.…

Computation and Language · Computer Science 2025-08-19 Xinbo Wu , Abhishek Umrawal , Lav R. Varshney

Language Models (LMs) have proven to be useful in various downstream applications, such as summarisation, translation, question answering and text classification. LMs are becoming increasingly important tools in Artificial Intelligence,…

Large Language Models (LLMs) have emerged as a dominant approach for a wide range of NLP tasks, with their access to external information further enhancing their capabilities. However, this introduces new vulnerabilities, known as prompt…

Computation and Language · Computer Science 2025-04-11 Ruiyi Zhang , David Sullivan , Kyle Jackson , Pengtao Xie , Mei Chen

Pre-trained language models (PLMs) have demonstrated significant proficiency in solving a wide range of general natural language processing (NLP) tasks. Researchers have observed a direct correlation between the performance of these models…

Computation and Language · Computer Science 2024-04-12 Kennedy Edemacu , Xintao Wu

Large language models (LLMs) require well-crafted prompts for effective use. Prompt engineering, the process of designing prompts, is challenging, particularly for non-experts who are less familiar with AI technologies. While researchers…

Human-Computer Interaction · Computer Science 2024-01-29 Zijie J. Wang , Aishwarya Chakravarthy , David Munechika , Duen Horng Chau

Soft prompts have been recently proposed as a tool for adapting large frozen language models (LMs) to new tasks. In this work, we repurpose soft prompts to the task of injecting world knowledge into LMs. We introduce a method to train soft…

Computation and Language · Computer Science 2022-10-11 Cicero Nogueira dos Santos , Zhe Dong , Daniel Cer , John Nham , Siamak Shakeri , Jianmo Ni , Yun-hsuan Sung

Chain-of-Thought (CoT) prompting methods have enabled large language models (LLMs) to generate reasoning paths and solve math word problems (MWPs). However, they are sensitive to mistakes in the paths, as any mistake can result in an…

Computation and Language · Computer Science 2023-12-13 Zhenyu Wu , Meng Jiang , Chao Shen

Large Language Models (LLMs) have shown prominent performance in various downstream tasks and prompt engineering plays a pivotal role in optimizing LLMs' performance. This paper, not only as an overview of current prompt engineering…

Computation and Language · Computer Science 2024-09-18 Haochen Li , Jonathan Leung , Zhiqi Shen

We present a novel class of jailbreak adversarial attacks on LLMs, termed Task-in-Prompt (TIP) attacks. Our approach embeds sequence-to-sequence tasks (e.g., cipher decoding, riddles, code execution) into the model's prompt to indirectly…

Cryptography and Security · Computer Science 2025-06-03 Sergey Berezin , Reza Farahbakhsh , Noel Crespi

Recent advances in molecular science have been propelled significantly by large language models (LLMs). However, their effectiveness is limited when relying solely on molecular sequences, which fail to capture the complex structures of…

Quantitative Methods · Quantitative Biology 2025-08-12 Jianting Tang , Yubo Wang , Haoyu Cao , Linli Xu

Large Language Model (LLM) Agents are an emerging computing paradigm that blends generative machine learning with tools such as code interpreters, web browsing, email, and more generally, external resources. These agent-based systems…

Cryptography and Security · Computer Science 2024-10-23 Xiaohan Fu , Shuheng Li , Zihan Wang , Yihao Liu , Rajesh K. Gupta , Taylor Berg-Kirkpatrick , Earlence Fernandes

The inference process of modern large language models (LLMs) demands prohibitive computational resources, rendering them infeasible for deployment on consumer-grade devices. To address this limitation, recent studies propose distributed LLM…

Cryptography and Security · Computer Science 2025-05-26 Xinjian Luo , Ting Yu , Xiaokui Xiao

One way to address safety risks from large language models (LLMs) is to censor dangerous knowledge from their training data. While this removes the explicit information, implicit information can remain scattered across various training…

Computation and Language · Computer Science 2024-12-24 Johannes Treutlein , Dami Choi , Jan Betley , Samuel Marks , Cem Anil , Roger Grosse , Owain Evans

Unlearning seeks to remove specific knowledge from large language models (LLMs), but its effectiveness remains contested. On one side, "forgotten" knowledge can often be recovered through interventions such as light fine-tuning; on the…

Computation and Language · Computer Science 2025-09-30 Qingjie Zhang , Haoting Qian , Zhicong Huang , Cheng Hong , Minlie Huang , Ke Xu , Chao Zhang , Han Qiu