English
Related papers

Related papers: SGHA-Attack: Semantic-Guided Hierarchical Alignmen…

200 papers

Currently, open-sourced large language models (OSLLMs) have demonstrated remarkable generative performance. However, as their structure and weights are made public, they are exposed to jailbreak attacks even after alignment. Existing…

Cryptography and Security · Computer Science 2026-03-16 Jinman Wu , Yi Xie , Shiqian Zhao , Xiaofeng Chen

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

Alignment in large language models (LLMs) is used to enforce guidelines such as safety. Yet, alignment fails in the face of jailbreak attacks that modify inputs to induce unsafe outputs. In this paper, we introduce and evaluate a new…

Cryptography and Security · Computer Science 2026-02-19 Jean-Charles Noirot Ferrand , Yohan Beugin , Eric Pauley , Ryan Sheatsley , Patrick McDaniel

Transfer adversarial attack is a non-trivial black-box adversarial attack that aims to craft adversarial perturbations on the surrogate model and then apply such perturbations to the victim model. However, the transferability of…

Machine Learning · Computer Science 2021-12-14 Shuman Fang , Jie Li , Xianming Lin , Rongrong Ji

Large Language Models (LLMs) have emerged as powerful tools for diverse applications. However, their uniform token processing paradigm introduces critical vulnerabilities in instruction handling, particularly when exposed to adversarial…

Cryptography and Security · Computer Science 2025-12-04 Tengyun Ma , Jiaqi Yao , Daojing He , Shihao Peng , Yu Li , Shaohui Liu , Zhuotao Tian

Vision-language pre-training (VLP) on large-scale image-text pairs has recently witnessed rapid progress for learning cross-modal representations. Existing pre-training methods either directly concatenate image representation and text…

Computation and Language · Computer Science 2021-03-16 Chenliang Li , Ming Yan , Haiyang Xu , Fuli Luo , Wei Wang , Bin Bi , Songfang Huang

The emerging paradigm of leveraging pretrained large language models (LLMs) for time series forecasting has predominantly employed linguistic-temporal modality alignment strategies through token-level or layer-wise feature mapping. However,…

Artificial Intelligence · Computer Science 2025-05-20 Siming Sun , Kai Zhang , Xuejun Jiang , Wenchao Meng , Qinmin Yang

Large Language Models (LLMs) and Vision-Language Large Models (LVLMs) have achieved remarkable progress in natural language processing and multimodal understanding. Despite their impressive generalization capabilities, current LVLMs often…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Leilei Guo , Antonio Carlos Rivera , Peiyu Tang , Haoxuan Ren , Zheyu Song

Hierarchical Text Classification (HTC) aims to categorize text data based on a structured label hierarchy, resulting in predicted labels forming a sub-hierarchy tree. The semantics of the text should align with the semantics of the labels…

Computation and Language · Computer Science 2024-09-04 Ashish Kumar , Durga Toshniwal

Large-scale Vision-Language Models (VLMs) such as CLIP learn powerful semantic representations but operate in Euclidean space, which fails to capture the inherent hierarchical structure of visual and linguistic concepts. Hyperbolic…

Computer Vision and Pattern Recognition · Computer Science 2026-03-25 Chuong Huynh , Hossein Souri , Abhinav Kumar , Vitali Petsiuk , Deen Dayal Mohan , Suren Kumar

Cross-modal alignment is an effective approach to improving visual classification. Existing studies typically enforce a one-step mapping that uses deep neural networks to project the visual features to mimic the distribution of textual…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Zixuan Li , Lei Meng , Guoqing Chao , Wei Wu , Xiaoshuo Yan , Yimeng Yang , Zhuang Qi , Xiangxu Meng

Vision-Language-Action (VLA) models enable robots to interpret natural-language instructions and perform diverse tasks, yet their integration of perception, language, and control introduces new safety vulnerabilities. Despite growing…

Cryptography and Security · Computer Science 2025-11-18 Jiayu Li , Yunhan Zhao , Xiang Zheng , Zonghuan Xu , Yige Li , Xingjun Ma , Yu-Gang Jiang

Vision-language models (VLMs) are increasingly used in autonomous driving because they combine visual perception with language-based reasoning, supporting more interpretable decision-making, yet their robustness to physical adversarial…

Computer Vision and Pattern Recognition · Computer Science 2026-05-01 David Fernandez , Pedram MohajerAnsari , Amir Salarpour , Mert D. Pese

Despite the strong performance of deep neural networks in modern Web and language applications, they remain vulnerable to adversarial attacks, especially transferable attacks that generate adversarial examples using surrogate models without…

Computation and Language · Computer Science 2026-05-26 Han Liu , Zhi Xu , Xiaotong Zhang , Feng Zhang , Xiaoming Xu , Wei Wang , Fenglong Ma , Hong Yu

Large vision-language models (LVLMs) integrate visual information into large language models, showcasing remarkable multi-modal conversational capabilities. However, the visual modules introduces new challenges in terms of robustness for…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Yubo Wang , Chaohu Liu , Yanqiu Qu , Haoyu Cao , Deqiang Jiang , Linli Xu

Vision-language-action (VLA) models have recently shown strong potential in enabling robots to follow language instructions and execute precise actions. However, most VLAs are built upon vision-language models pretrained solely on 2D data,…

Robotics · Computer Science 2025-10-20 Fuhao Li , Wenxuan Song , Han Zhao , Jingbo Wang , Pengxiang Ding , Donglin Wang , Long Zeng , Haoang Li

Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool another model. However,…

Machine Learning · Computer Science 2018-11-22 Qian Huang , Zeqi Gu , Isay Katsman , Horace He , Pian Pawakapan , Zhiqiu Lin , Serge Belongie , Ser-Nam Lim

Heterogeneous Graph Neural Networks (HGNNs) are increasingly recognized for their performance in areas like the web and e-commerce, where resilience against adversarial attacks is crucial. However, existing adversarial attack methods, which…

Machine Learning · Computer Science 2024-01-19 He Zhao , Zhiwei Zeng , Yongwei Wang , Deheng Ye , Chunyan Miao

Despite inheriting security measures from underlying language models, Vision-Language Models (VLMs) may still be vulnerable to safety alignment issues. Through empirical analysis, we uncover two critical findings: scenario-matched images…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Shuyang Hao , Bryan Hooi , Jun Liu , Kai-Wei Chang , Zi Huang , Yujun Cai

The emergence of vision-language-action models (VLAs) for end-to-end control is reshaping the field of robotics by enabling the fusion of multimodal sensory inputs at the billion-parameter scale. The capabilities of VLAs stem primarily from…

‹ Prev 1 4 5 6 7 8 10 Next ›