English
Related papers

Related papers: Targeted Bit-Flip Attacks on LLM-Based Agents

200 papers

In this paper, we delve into the susceptibility of federated medical image analysis systems to adversarial attacks. Our analysis uncovers a novel exploitation avenue: using gradient information from prior global model updates, adversaries…

Machine Learning · Computer Science 2023-10-24 Erfan Darzi , Florian Dubost , Nanna. M. Sijtsema , P. M. A van Ooijen

Most LLM safety work studies single-agent models, but many real applications rely on multiple interacting agents. In these systems, prompt segmentation and inter-agent routing create attack surfaces that single-agent evaluations miss. We…

Multiagent Systems · Computer Science 2026-04-21 Nokimul Hasan Arif , Qian Lou , Mengxin Zheng

Recent advances in Vision-Language Models (VLMs) have propelled embodied agents by enabling direct perception, reasoning, and planning task-oriented actions from visual inputs. However, such vision-driven embodied agents open a new attack…

Artificial Intelligence · Computer Science 2026-02-24 Qiusi Zhan , Hyeonjeong Ha , Rui Yang , Sirui Xu , Hanyang Chen , Liang-Yan Gui , Yu-Xiong Wang , Huan Zhang , Heng Ji , Daniel Kang

Large language models (LLMs) are widely deployed, but their substantial compute demands make them vulnerable to inference cost attacks that aim to deliberately maximize the output length. In this work, we investigate a distinct attack…

Cryptography and Security · Computer Science 2026-02-24 Xiaobei Yan , Yiming Li , Hao Wang , Han Qiu , Tianwei Zhang

Today, models capable of working with various modalities simultaneously in a chat format are gaining increasing popularity. Despite this, there is an issue of potential attacks on these models, especially considering that many of them…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Viacheslav Iablochnikov , Alexander Rogachev

Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against…

Cryptography and Security · Computer Science 2026-03-23 Shawn Li , Yue Zhao

Security of machine learning is increasingly becoming a major concern due to the ubiquitous deployment of deep learning in many security-sensitive domains. Many prior studies have shown external attacks such as adversarial examples that…

Cryptography and Security · Computer Science 2020-04-01 Fan Yao , Adnan Siraj Rakin , Deliang Fan

Bit Flip Attacks (BFAs) are a well-established class of adversarial attacks, originally developed for Convolutional Neural Networks within the computer vision domain. Most recently, these attacks have been extended to target Graph Neural…

Machine Learning · Computer Science 2025-04-21 Lorenz Kummer , Samir Moustafa , Wilfried Gansterer , Nils Kriege

Large Language Model-based Multi-Agent Systems (LLM-MAS) have revolutionized complex problem-solving capability by enabling sophisticated agent collaboration through message-based communications. While the communication framework is crucial…

Cryptography and Security · Computer Science 2025-06-03 Pengfei He , Yupin Lin , Shen Dong , Han Xu , Yue Xing , Hui Liu

Large language models (LLMs) have demonstrated impressive results on natural language tasks, and security researchers are beginning to employ them in both offensive and defensive systems. In cyber-security, there have been multiple research…

Cryptography and Security · Computer Science 2024-03-05 Jiacen Xu , Jack W. Stokes , Geoff McDonald , Xuesong Bai , David Marshall , Siyue Wang , Adith Swaminathan , Zhou Li

Current Large Language Models (LLMs) are gradually exploited in practically valuable agentic workflows such as Deep Research, E-commerce recommendation, and job recruitment. In these applications, LLMs need to select some optimal solutions…

Computers and Society · Computer Science 2026-03-23 Zichen Tang , Zirui Zhang , Qian Wang , Zhenheng Tang , Bo Li , Xiaowen Chu

We study a new vulnerability in commercial-scale safety-aligned large language models (LLMs): their refusal to generate harmful responses can be broken by flipping only a few bits in model parameters. Our attack jailbreaks billion-parameter…

Cryptography and Security · Computer Science 2025-10-06 Zachary Coalson , Jeonghyun Woo , Chris S. Lin , Joyce Qu , Yu Sun , Shiyang Chen , Lishan Yang , Gururaj Saileshwar , Prashant Nair , Bo Fang , Sanghyun Hong

Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples. While existing methods typically achieve targeted attacks by aligning global features-such as CLIP's [CLS] token-between adversarial and target…

Computer Vision and Pattern Recognition · Computer Science 2025-05-28 Xiaojun Jia , Sensen Gao , Simeng Qin , Tianyu Pang , Chao Du , Yihao Huang , Xinfeng Li , Yiming Li , Bo Li , Yang Liu

Foundation models (FMs) for computer vision learn rich and robust representations, enabling their adaptation to task/domain-specific deployments with little to no fine-tuning. However, we posit that the very same strength can make…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Ankita Raj , Deepankar Varma , Chetan Arora

In recent years, large language models (LLMs) have become increasingly capable and can now interact with tools (i.e., call functions), read documents, and recursively call themselves. As a result, these LLMs can now function autonomously as…

Cryptography and Security · Computer Science 2024-02-19 Richard Fang , Rohan Bindu , Akul Gupta , Qiusi Zhan , Daniel Kang

LLM-based multi-agent systems (MAS) demonstrate increasing integration into next-generation applications, but their safety in backdoor attacks remains largely underexplored. However, existing research has focused exclusively on single-agent…

Cryptography and Security · Computer Science 2025-10-14 Pengyu Zhu , Lijun Li , Yaxing Lyu , Li Sun , Sen Su , Jing Shao

Large language models (LLMs) have empowered nodes within multi-agent networks with intelligence, showing growing applications in both academia and industry. However, how to prevent these networks from generating malicious information…

Multiagent Systems · Computer Science 2024-10-22 Miao Yu , Shilong Wang , Guibin Zhang , Junyuan Mao , Chenlong Yin , Qijiong Liu , Qingsong Wen , Kun Wang , Yang Wang

LLM-integrated applications and agents are vulnerable to prompt injection attacks, where adversaries embed malicious instructions within seemingly benign input data to manipulate the LLM's intended behavior. Recent defenses based on…

Cryptography and Security · Computer Science 2025-12-09 Sarthak Choudhary , Divyam Anshumaan , Nils Palumbo , Somesh Jha

Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, their increasing autonomy also introduces a new attack surface: adversarial interactions…

Artificial Intelligence · Computer Science 2026-05-05 Sheldon Yu , Yingcheng Sun , Hanqing Guo , Julian McAuley , Qianqian Tong

Autonomous agentic AI systems powered by vision-language models (VLMs) are rapidly advancing toward real-world deployment, yet their cross-modal reasoning capabilities introduce new attack surfaces for adversarial manipulation that exploit…

Artificial Intelligence · Computer Science 2025-11-25 Hangoo Kang , Jehyeok Yeon , Gagandeep Singh