English
Related papers

Related papers: Multi-Level Safety Continual Projection for Fine-T…

200 papers

Safety alignment of large language models (LLMs) has been gaining increasing attention. However, current safety-aligned LLMs suffer from the fragile and imbalanced safety mechanisms, which can still be induced to generate unsafe responses,…

Computation and Language · Computer Science 2024-12-18 Weixiang Zhao , Yulin Hu , Zhuojun Li , Yang Deng , Jiahe Guo , Xingyu Sui , Yanyan Zhao , Bing Qin , Tat-Seng Chua , Ting Liu

The deployment of multimodal large language models (MLLMs) has brought forth a unique vulnerability: susceptibility to malicious attacks through visual inputs. This paper investigates the novel challenge of defending MLLMs against such…

Cryptography and Security · Computer Science 2024-06-18 Renjie Pi , Tianyang Han , Jianshu Zhang , Yueqi Xie , Rui Pan , Qing Lian , Hanze Dong , Jipeng Zhang , Tong Zhang

The Model Context Protocol (MCP) enables Large Language Models (LLMs) to interact with external tools via tool descriptors, thereby extending their capabilities for task execution, autonomous decision-making, and multi-agent coordination.…

Cryptography and Security · Computer Science 2026-05-22 Saeid Jamshidi , Arghavan Moradi Dakhel , Kawser Wazed Nafi , Foutse Khomh

Large Language Models (LLMs) have recently emerged as planners for language-instructed agents, generating sequences of actions to accomplish natural language tasks. However, their reliability remains a challenge, especially in long-horizon…

Robotics · Computer Science 2025-11-11 Jun Wang , Yevgeniy Vorobeychik , Yiannis Kantaros

The Model Context Protocol (MCP) enables large language models (LLMs) to dynamically discover and invoke third-party tools, significantly expanding agent capabilities while introducing a distinct security landscape. Unlike prompt-only…

Cryptography and Security · Computer Science 2026-04-10 Mehrdad Rostamzadeh , Sidhant Narula , Nahom Birhan , Mohammad Ghasemigol , Daniel Takabi

Fine-tuning safety-aligned large language models (LLMs) can substantially compromise their safety. Previous approaches require many safety samples or calibration sets, which not only incur significant computational overhead during…

Machine Learning · Computer Science 2026-01-07 Jiawen Zhang , Lipeng He , Kejia Chen , Jian Lou , Jian Liu , Xiaohu Yang , Ruoxi Jia

Current vision large language models (VLLMs) exhibit remarkable capabilities yet are prone to generate harmful content and are vulnerable to even the simplest jailbreaking attacks. Our initial analysis finds that this is due to the presence…

Machine Learning · Computer Science 2024-06-19 Yongshuo Zong , Ondrej Bohdal , Tingyang Yu , Yongxin Yang , Timothy Hospedales

Large language models (LLMs) have achieved remarkable success across many applications, but their ability to generate harmful content raises serious safety concerns. Although safety alignment techniques are often applied during pre-training…

Machine Learning · Computer Science 2026-04-24 Chengcan Wu , Zhixin Zhang , Zeming Wei , Yihao Zhang , Xiaokun Luan , Meng Sun

Fine-tuning-as-a-service, while commercially successful for Large Language Model (LLM) providers, exposes models to harmful fine-tuning attacks. As a widely explored defense paradigm against such attacks, unlearning attempts to remove…

Cryptography and Security · Computer Science 2025-05-23 Biao Yi , Tiansheng Huang , Baolei Zhang , Tong Li , Lihai Nie , Zheli Liu , Li Shen

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks,…

Computation and Language · Computer Science 2024-11-11 Md Abdur Rahman , Fan Wu , Alfredo Cuzzocrea , Sheikh Iqbal Ahamed

Language models (LMs) trained on vast quantities of unlabelled data have greatly advanced the field of natural language processing (NLP). In this study, we re-visit the widely accepted notion in NLP that continued pre-training LMs on…

Computation and Language · Computer Science 2023-10-09 Zhengxiang Shi , Aldo Lipani

Ensuring safety alignment is a critical requirement for large language models (LLMs), particularly given increasing deployment in real-world applications. Despite considerable advancements, LLMs remain susceptible to jailbreak attacks,…

Cryptography and Security · Computer Science 2025-06-02 Xin Yi , Yue Li , Dongsheng Shi , Linlin Wang , Xiaoling Wang , Liang He

Vision-Language Pre-training (VLP) models like CLIP have significantly advanced Remote Sensing Image-Text Retrieval (RSITR). However, existing methods predominantly rely on coarse-grained global alignment, which often overlooks the dense,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Yifan Li , Shiying Wang , Jianqiang Huang

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

Machine Learning · Computer Science 2025-08-22 Xiangman Li , Xiaodong Wu , Qi Li , Jianbing Ni , Rongxing Lu

The model context protocol (MCP) has been widely adapted as an open standard enabling the seamless integration of generative AI agents. However, recent work has shown the MCP is susceptible to retrieval-based "falsely benign" attacks…

Machine Learning · Computer Science 2025-05-30 John Halloran

Large language models (LLMs) have shown remarkable in-context learning (ICL) capabilities, yet their potential for sequential decision-making remains underexplored. In this paper, we study the ICL capabilities of LLMs in sequential…

Machine Learning · Computer Science 2026-05-12 Minmin Zhang , Sina Aghaei , Soroush Saghafian

The safety of large language models (LLMs) has increasingly emerged as a fundamental aspect of their development. Existing safety alignment for LLMs is predominantly achieved through post-training methods, which are computationally…

Artificial Intelligence · Computer Science 2026-02-03 Sicheng Shen , Mingyang Lv , Han Shen , Jialin Wu , Binghao Wang , Zhou Yang , Guobin Shen , Dongcheng Zhao , Feifei Zhao , Yi Zeng

The robustness and security of large language models (LLMs) has become a prominent research area. One notable vulnerability is the ability to bypass LLM safeguards by translating harmful queries into rare or underrepresented languages, a…

Computation and Language · Computer Science 2025-09-16 Hongliang Li , Jinan Xu , Gengping Cui , Changhao Guan , Fengran Mo , Kaiyu Huang

The Model Context Protocol (MCP) enhances large language models (LLMs) by integrating external tools, enabling dynamic aggregation of real-time data to improve task execution. However, its non-isolated execution context introduces critical…

Computation and Language · Computer Science 2025-08-11 Haoran Shi , Hongwei Yao , Shuo Shao , Shaopeng Jiao , Ziqi Peng , Zhan Qin , Cong Wang

By incorporating visual inputs, Multimodal Large Language Models (MLLMs) extend LLMs to support visual reasoning. However, this integration also introduces new vulnerabilities, making MLLMs susceptible to multimodal jailbreak attacks and…

Cryptography and Security · Computer Science 2025-12-04 Beitao Chen , Xinyu Lyu , Lianli Gao , Jingkuan Song , Heng Tao Shen