English
Related papers

Related papers: Doppelganger Method: Breaking Role Consistency in …

200 papers

Current LLM alignment methods are readily broken through specifically crafted adversarial prompts. While crafting adversarial prompts using discrete optimization is highly effective, such attacks typically use more than 100,000 LLM calls.…

Machine Learning · Computer Science 2025-03-04 Simon Geisler , Tom Wollschläger , M. H. I. Abdalla , Johannes Gasteiger , Stephan Günnemann

Universal goal hijacking is a kind of prompt injection attack that forces LLMs to return a target malicious response for arbitrary normal user prompts. The previous methods achieve high attack performance while being too cumbersome and…

Computation and Language · Computer Science 2025-06-02 Yihao Huang , Chong Wang , Xiaojun Jia , Qing Guo , Felix Juefei-Xu , Jian Zhang , Geguang Pu , Yang Liu

Prompt injection attacks, where untrusted data contains an injected prompt to manipulate the system, have been listed as the top security threat to LLM-integrated applications. Model-level prompt injection defenses have shown strong…

Cryptography and Security · Computer Science 2026-02-09 Sizhe Chen , Arman Zharmagambetov , David Wagner , Chuan Guo

Decompositional jailbreaks pose a critical threat to large language models (LLMs) by allowing adversaries to fragment a malicious objective into a sequence of individually benign queries that collectively reconstruct prohibited content. In…

Cryptography and Security · Computer Science 2026-05-01 Bowen Sun , Chaozhuo Li , Yaodong Yang , Yiwei Wang , Chaowei Xiao

The exploitation of large language models (LLMs) for malicious purposes poses significant security risks as these models become more powerful and widespread. While most existing red-teaming frameworks focus on single-turn attacks,…

Artificial Intelligence · Computer Science 2025-04-03 Si Chen , Xiao Yu , Ninareh Mehrabi , Rahul Gupta , Zhou Yu , Ruoxi Jia

Large language models (LLMs) have gained widespread adoption across diverse applications due to their impressive generative capabilities. Their plug-and-play nature enables both developers and end users to interact with these models through…

Cryptography and Security · Computer Science 2025-10-21 Zongze Li , Jiawei Guo , Haipeng Cai

This paper proposes a game theoretic framework that models the interaction between prompt engineers and large language models (LLMs) as a two player extensive form game coupled with a Rapidly exploring Random Trees (RRT) search over prompt…

Artificial Intelligence · Computer Science 2026-03-04 Zhengye Han , Quanyan Zhu

The advent of tool-using LLM agents shifts safety monitoring from output moderation to auditing long, noisy interaction trajectories, where risk-critical evidence is sparse-making standard binary supervision poorly suited for credit…

Machine Learning · Computer Science 2026-04-07 Lin Wang , Junfeng Fang , Dan Zhang , Fei Shen , Xiang Wang , Tat-Seng Chua

Security alignment enables the Large Language Model (LLM) to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this security mechanism. Previous studies have isolated LLM…

Cryptography and Security · Computer Science 2025-08-07 Xiaohu Li , Yunfeng Ning , Zepeng Bao , Mayi Xu , Jianhao Chen , Tieyun Qian

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

Multi-agent systems coordinate LLM-based agents to perform tasks on users' behalf. In real-world applications, multi-agent systems will inevitably interact with untrusted inputs, such as malicious Web content, files, email attachments, and…

Cryptography and Security · Computer Science 2025-09-16 Harold Triedman , Rishi Jha , Vitaly Shmatikov

Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks. However, the adversarial attack task has found that PLMs are vulnerable to small perturbations. Mainstream methods adopt a detached two-stage…

Computation and Language · Computer Science 2023-05-30 Xuanjie Fang , Sijie Cheng , Yang Liu , Wei Wang

Modern large language models (LLMs), such as ChatGPT, have demonstrated impressive capabilities for coding tasks including writing and reasoning about code. They improve upon previous neural network models of code, such as code2seq or…

Machine Learning · Computer Science 2023-11-23 Chi Zhang , Zifan Wang , Ravi Mangal , Matt Fredrikson , Limin Jia , Corina Pasareanu

As Large Language Models (LLMs) are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from…

Machine Learning · Computer Science 2025-05-16 Sajib Biswas , Mao Nishino , Samuel Jacob Chacko , Xiuwen Liu

With the enhanced performance of large models on natural language processing tasks, potential moral and ethical issues of large models arise. There exist malicious attackers who induce large models to jailbreak and generate information…

Artificial Intelligence · Computer Science 2024-04-04 Qianqiao Xu , Zhiliang Tian , Hongyan Wu , Zhen Huang , Yiping Song , Feng Liu , Dongsheng Li

The drastic increase of large language models' (LLMs) parameters has led to a new research direction of fine-tuning-free downstream customization by prompts, i.e., task descriptions. While these prompt-based services (e.g. OpenAI's GPTs)…

Computation and Language · Computer Science 2025-02-13 Zi Liang , Haibo Hu , Qingqing Ye , Yaxin Xiao , Haoyang Li

Large Language Models (LLMs) have seen rapid adoption in recent years, with industries increasingly relying on them to maintain a competitive advantage. These models excel at interpreting user instructions and generating human-like…

Cryptography and Security · Computer Science 2025-09-09 Andrew Yeo , Daeseon Choi

The integration of large language models (LLMs) into a wide range of applications has highlighted the critical role of well-crafted system prompts, which require extensive testing and domain expertise. These prompts enhance task performance…

Cryptography and Security · Computer Science 2026-04-30 Zhixiong Zhuang , Maria-Irina Nicolae , Hui-Po Wang , Mario Fritz

Tool-Based Agent Systems (TBAS) allow Language Models (LMs) to use external tools for tasks beyond their standalone capabilities, such as searching websites, booking flights, or making financial transactions. However, these tools greatly…

Cryptography and Security · Computer Science 2025-02-17 Peter Yong Zhong , Siyuan Chen , Ruiqi Wang , McKenna McCall , Ben L. Titzer , Heather Miller , Phillip B. Gibbons

As LLM agents transition from digital assistants to physical controllers in autonomous systems and robotics, they face an escalating threat from indirect prompt injection. By embedding adversarial instructions into the results of tool…

Artificial Intelligence · Computer Science 2026-01-09 Qiang Yu , Xinran Cheng , Chuanyi Liu