SEEM: Exploiting Black-Box Text Attacks to Manipulate Tool Selection
New Laboratory of Pattern Recognition (NLPR)(模式识别国家重点实验室);State Key Laboratory of Multimodal Artificial Intelligence Systems(多模态人工智能系统全国重点实验室);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Beijing University of Posts and Telecommunications(北京邮电大学)
Liuji Chen, Hao Gao, Jinghao Zhang, Qiang Liu, Shu Wu, Liang Wang
备注:
2026 IEEE International Conference on Acoustics, Speech, and Signal Processing
Tool learning has emerged as a powerful auxiliary mechanism that extends the capabilities of large language models (LLMs), enabling them to address complex tasks that demand real-time relevance or high-precision operations. However, beneath this strength lie significant security risks. Prior studies have primarily concentrated on corrupting the outputs of invoked tools, while largely overlooking the vulnerability of the tool selection process itself. To bridge this gap, we introduce a black-box, text-based attack that substantially increases the likelihood of a target tool being selected. We propose SEEM, a two-level coarse-to-fine perturbation method that operates at both the word and character levels. Through comprehensive experiments, we show that merely perturbing the textual information of tools can markedly raise the probability of the target tool being prioritized and ranked higher among candidates. Our findings expose critical weaknesses in the tool selection mechanism and lay the groundwork for developing defenses to secure this essential process.
Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior
Graduate School of Advanced Science and Engineering(先进科学与工程研究生学校);Hiroshima University(广岛大学);Graduate School of Science and Engineering(科学与工程研究生学校);Hosei University(立命馆大学);School of Mathematics and Computer Science(数学与计算机科学学院);Tongling University(铜陵大学);School of Computer Science and Engineering(计算机科学与工程学院);University of Aizu(立海大学)
Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models
School of Economics and Management(经济管理学院);East China Normal University(华东师范大学);School of Information Science and Technology(信息科学与技术学院);Shanghai Tech University(上海理工大学);Shanghai Development Center of Computer Software Technology(上海计算机软件技术开发中心);School of Computer and Information Engineering(计算机与信息工程学院);Shanghai Polytechnic University(上海理工大学)
Exploiting Layer-Specific Vulnerabilities to Backdoor Attack in Federated Learning
School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran(塔里斯坦大学电气与计算机工程学院);School of Electrical and Computer Engineering, Shiraz University, Shiraz, Iran(谢尔兹大学电气与计算机工程学院);Okinawa Institute of Science and Technology, Okinawa, Japan(冲绳科学技术研究院);School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Tehran, Iran(基础科学研究院(IPM)计算机科学学院)