English
Related papers

Related papers: Harnessing Hyperbolic Geometry for Harmful Prompt …

200 papers

Large Language Models (LLMs) are increasingly used for decision making in embodied agents, yet existing safety evaluations often rely on coarse success rates and domain-specific setups, making it difficult to diagnose why and where these…

Artificial Intelligence · Computer Science 2025-05-27 Yejin Son , Minseo Kim , Sungwoong Kim , Seungju Han , Jian Kim , Dongju Jang , Youngjae Yu , Chanyoung Park

Aligning Vision-Language Models (VLMs) with safety standards is essential to mitigate risks arising from their multimodal complexity, where integrating vision and language unveils subtle threats beyond the reach of conventional safeguards.…

Machine Learning · Computer Science 2025-10-14 Menglan Chen , Xianghe Pang , Jingjing Dong , WenHao Wang , Yaxin Du , Siheng Chen

Vision-language models (VLMs) have demonstrated exceptional generalization capabilities for downstream tasks. Due to its efficiency, prompt learning has gradually become a more effective and efficient method for transferring VLMs to…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Chenhao Ding , Xinyuan Gao , Songlin Dong , Jizhou Han , Qiang Wang , Zhengdong Zhou , Yuhang He , Yihong Gong

Deploying large vision-language models (LVLMs) introduces a unique vulnerability: susceptibility to malicious attacks via visual inputs. However, existing defense methods suffer from two key limitations: (1) They solely focus on textual…

Cryptography and Security · Computer Science 2025-03-17 Shuyang Hao , Yiwei Wang , Bryan Hooi , Ming-Hsuan Yang , Jun Liu , Chengcheng Tang , Zi Huang , Yujun Cai

The safety alignment of Large Language Models (LLMs) remains vulnerable to Harmful Fine-tuning (HFT). While existing defenses impose constraints on parameters, gradients, or internal representations, we observe that they can be effectively…

Cryptography and Security · Computer Science 2026-05-11 Guoxin Lu , Letian Sha , Qing Wang , Peijie Sun , Hao Zhou , Hua Dai , Fu Xiao

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

This study addresses critical gaps in Automated Essay Scoring (AES) systems and Large Language Models (LLMs) with regard to their ability to effectively identify and score harmful essays. Despite advancements in AES technology, current…

Computation and Language · Computer Science 2026-01-12 Hongjin Kim , Jeonghyun Kang , Harksoo Kim

Large Vision-Language Models (LVLMs) undergo safety alignment to suppress harmful content. However, current defenses predominantly target explicit malicious patterns in the input representation, often overlooking the vulnerabilities…

Cryptography and Security · Computer Science 2026-03-11 Quanchen Zou , Moyang Chen , Zonghao Ying , Wenzhuo Xu , Yisong Xiao , Deyue Zhang , Dongdong Yang , Zhao Liu , Xiangzheng Zhang

Recent advances have witnessed the effectiveness of reinforcement learning (RL) finetuning in enhancing the reasoning capabilities of large language models (LLMs). The optimization process often requires numerous iterations to achieve…

Artificial Intelligence · Computer Science 2026-01-13 Yun Qu , Qi Wang , Yixiu Mao , Vincent Tao Hu , Björn Ommer , Xiangyang Ji

Large Language Models (LLMs) are prone to off-topic misuse, where users may prompt these models to perform tasks beyond their intended scope. Current guardrails, which often rely on curated examples or custom classifiers, suffer from high…

Computation and Language · Computer Science 2025-04-10 Gabriel Chua , Shing Yee Chan , Shaun Khoo

Large language models (LLMs) are advanced AI systems applied across various domains, including NLP, information retrieval, and recommendation systems. Despite their adaptability and efficiency, LLMs have not been extensively explored for…

Artificial Intelligence · Computer Science 2025-07-08 Harshith Manjunath , Lucas Heublein , Tobias Feigl , Felix Ott

Visual environments are inherently hierarchical, as a panoramic view naturally encompasses and organizes multiple perspective views within its field. Capturing this hierarchy is crucial for effective perspective-to-equirectangular (P2E)…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Suhan Woo , Seongwon Lee , Jinwoo Jang , Euntai Kim

Large Vision-Language Models (LVLMs) are vulnerable to a growing array of multimodal jailbreak attacks, necessitating defenses that are both generalizable to novel threats and efficient for practical deployment. Many current strategies fall…

Cryptography and Security · Computer Science 2026-04-21 Peichun Hua , Hao Li , Shanghao Shi , Zhiyuan Yu , Ning Zhang

The proliferation of Large Language Models (LLMs) has introduced critical security challenges, where adversarial actors can manipulate input prompts to cause significant harm and circumvent safety alignments. These prompt-based attacks…

Large Vision-Language Models (LVLMs) have transformed multi-modal understanding, excelling in tasks like image captioning and visual question answering by integrating visual and textual inputs. However, their robustness against adversarial…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Xiang Fang , Wanlong Fang , Changshuo Wang

Detecting harmful memes is crucial for safeguarding the integrity and harmony of online environments, yet existing detection methods are often resource-intensive, inflexible, and lacking explainability, limiting their applicability in…

Computation and Language · Computer Science 2026-01-29 Fengjun Pan , Xiaobao Wu , Tho Quan , Anh Tuan Luu

Multi-prompt learning methods have emerged as an effective approach for facilitating the rapid adaptation of vision-language models to downstream tasks with limited resources. Existing multi-prompt learning methods primarily focus on…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Fei Song , Yi Li , Jiangmeng Li , Rui Wang , Changwen Zheng , Fanjiang Xu , Hui Xiong

Prompt learning is an effective method to customize Vision-Language Models (VLMs) for various downstream tasks, involving tuning very few parameters of input prompt tokens. Recently, prompt pretraining in large-scale dataset (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-11 Zhenyuan Chen , Lingfeng Yang , Shuo Chen , Zhaowei Chen , Jiajun Liang , Xiang Li

Large Language Models (LLMs) have demonstrated remarkable performance across various tasks by effectively utilizing a prompting strategy. However, they are highly sensitive to input perturbations, such as typographical errors or slight…

Computation and Language · Computer Science 2026-05-27 Lin Mu , Guowei Chu , Li Ni , Lei Sang , Yiwen Zhang

Large Language Models (LLMs) generating unsafe responses to toxic prompts is a significant issue in their applications. While various efforts aim to address this safety concern, previous approaches often demand substantial human data…

Computation and Language · Computer Science 2024-12-12 Yuxiao Lu , Arunesh Sinha , Pradeep Varakantham