English
Related papers

Related papers: Prompt Injection as Role Confusion

200 papers

Large Language Models (LLMs) can comply with harmful instructions, raising serious safety concerns despite their impressive capabilities. Recent work has leveraged probing-based approaches to study the separability of malicious and benign…

Computation and Language · Computer Science 2025-12-16 Cheng Wang , Zeming Wei , Qin Liu , Muhao Chen

The zero-shot chain of thought (CoT) approach is often used in question answering (QA) by language models (LMs) for tasks that require multiple reasoning steps. However, some QA tasks hinge more on accessing relevant knowledge than on…

Computation and Language · Computer Science 2025-05-27 Jiacan Yu , Hannah An , Lenhart K. Schubert

Large language models (LLMs) and their applications, such as agents, are highly vulnerable to prompt injection attacks. State-of-the-art prompt injection detection methods have the following limitations: (1) their effectiveness degrades…

Cryptography and Security · Computer Science 2026-04-02 Yanting Wang , Wei Zou , Runpeng Geng , Jinyuan Jia

We localize the policy routing mechanism in alignment-trained language models. An intermediate-layer attention gate reads detected content and triggers deeper amplifier heads that boost the signal toward refusal. In smaller models the gate…

Computation and Language · Computer Science 2026-05-04 Gregory N. Frank

Conversational large language models (LLMs) have gained widespread attention due to their instruction-following capabilities. To ensure conversational LLMs follow instructions, role separators are employed to distinguish between different…

Computation and Language · Computer Science 2025-04-09 Xitao Li , Haijun Wang , Jiang Wu , Ting Liu

As large language models (LLMs) are increasingly deployed as interactive agents, open-ended human-AI interactions can involve deceptive behaviors with serious real-world consequences, yet existing evaluations remain largely…

Artificial Intelligence · Computer Science 2026-02-09 Yichen Wu , Qianqian Gao , Xudong Pan , Geng Hong , Min Yang

Large Language Models (LLMs) are increasingly powerful but remain vulnerable to prompt injection attacks, where malicious inputs cause the model to deviate from its intended instructions. This paper introduces Sentinel, a novel detection…

Cryptography and Security · Computer Science 2025-06-09 Dror Ivry , Oran Nahum

We investigate opinion dynamics in a fully-connected system, consisting of $n$ identical and anonymous agents, where one of the opinions (which is called correct) represents a piece of information to disseminate. In more detail, one source…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-02-20 Luca Becchetti , Andrea Clementi , Amos Korman , Francesco Pasquale , Luca Trevisan , Robin Vacus

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

Large Language Models (LLMs) are gaining traction as a method to generate consensus statements and aggregate preferences in digital democracy experiments. Yet, LLMs could introduce critical vulnerabilities in these systems. Here, we examine…

Computers and Society · Computer Science 2026-03-03 Jairo Gudiño-Rosero , Clément Contet , Umberto Grandi , César A. Hidalgo

Large Language Models (LLMs) are increasingly integrated into real-world applications, from virtual assistants to autonomous agents. However, their flexibility also introduces new attack vectors-particularly Prompt Injection (PI), where…

Cryptography and Security · Computer Science 2025-09-17 Mengxiao Wang , Yuxuan Zhang , Guofei Gu

With the rapid development of Large Language Models (LLMs), numerous mature applications of LLMs have emerged in the field of content safety detection. However, we have found that LLMs exhibit blind trust in safety detection agents. The…

Cryptography and Security · Computer Science 2024-10-15 Yupeng Ren

Writing effective prompts for large language models (LLM) can be unintuitive and burdensome. In response, services that optimize or suggest prompts have emerged. While such services can reduce user effort, they also introduce a risk: the…

Cryptography and Security · Computer Science 2025-03-03 Weiran Lin , Anna Gerchanovsky , Omer Akgul , Lujo Bauer , Matt Fredrikson , Zifan Wang

As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing threats are prompt…

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

Large Language Models face security threats from jailbreak attacks. Existing research has predominantly focused on prompt-level attacks while largely ignoring the underexplored attack surface of user-controlled response prefilling. This…

Cryptography and Security · Computer Science 2025-08-27 Yakai Li , Jiekang Hu , Weiduan Sang , Luping Ma , Dongsheng Nie , Weijuan Zhang , Aimin Yu , Yi Su , Qingjia Huang , Qihang Zhou

User models in information retrieval rest on a foundational assumption that observed behavior reveals intent. This assumption collapses when the user is an AI agent privately configured by a human operator. For any action an agent takes, a…

Safety-aligned language models often refuse prompts that are actually harmless. Current evaluations mostly report global rates such as false rejection or compliance. These scores treat each prompt alone and miss local inconsistency, where a…

Computation and Language · Computer Science 2025-12-22 Riad Ahmed Anonto , Md Labid Al Nahiyan , Md Tanvir Hassan

Language models are susceptible to bias, sycophancy, backdoors, and other tendencies that lead to unfaithful responses to the input context. Interpreting internal states of language models could help monitor and correct unfaithful behavior.…

Computation and Language · Computer Science 2024-12-10 Jiahai Feng , Stuart Russell , Jacob Steinhardt

Masked language models like BERT can perform text classification in a zero-shot fashion by reformulating downstream tasks as text infilling. However, this approach is highly sensitive to the template used to prompt the model, yet…

Computation and Language · Computer Science 2022-10-27 Mozes van de Kar , Mengzhou Xia , Danqi Chen , Mikel Artetxe
‹ Prev 1 3 4 5 6 7 10 Next ›