大模型对齐与安全

Understanding the Supply Chain and Risks of Large Language Model Applications

Yujie Ma, Lili Quan, Xiaofei Xie, Qiang Hu, Jiongchi Yu, Yao Zhang, Sen Chen

专题命中 安全评测 ：trustworthy(abstract)

Comments 26 pages

Exploring the Potential of LLMs for Serendipity Evaluation in Recommender Systems

Li Kang, Yuhan Zhao, Li Chen

专题命中 安全评测 ：alignment(abstract)

Comments RecSys2025

BenchDepth: Are We on the Right Way to Evaluate Depth Foundation Models?

Zhenyu Li, Haotong Lin, Jiashi Feng, Peter Wonka, Bingyi Kang

机构 * KAUST（王国塔大学） ； ByteDance Seed（字节跳动种子） ； Zhejiang University（浙江大学） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments Webpage: https://zhyever.github.io/benchdepth

BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion Model

Weilin Lin, Nanjun Zhou, Yanyun Wang, Jianze Li, Hui Xiong, Li Liu

专题命中 安全评测 ：trustworthy(abstract)

CRAFT: A Neuro-Symbolic Framework for Visual Functional Affordance Grounding

Zhou Chen, Joe Lin, Sathyanarayanan N. Aakur

机构 * Auburn University（亚伯拉罕大学） 纠错

专题命中 安全评测 ：trustworthy(abstract)

Comments Accepted to NeSy 2025

Evaluation of Human Visual Privacy Protection: A Three-Dimensional Framework and Benchmark Dataset

Sara Abdulaziz, Giacomo D'Amicantonio, Egor Bondarev

机构 * Eindhoven University of Technology（埃因霍温理工大学） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments accepted at ICCV'25 workshop CV4BIOM

LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead

Junda He, Christoph Treude, David Lo

专题命中 安全评测 ：trustworthy(abstract)

Comments TOSEM 2030 Special Issue

Robustness Requirement Coverage using a Situation Coverage Approach for Vision-based AI Systems

Sepeedeh Shahbeigi, Nawshin Mannan Proma, Victoria Hodge, Richard Hawkins, Boda Li, Valentina Donzella

机构 * Department of Computer Science（计算机科学系） ； University of York（约克大学） ； WMG（沃林汉姆工学院） ； University of Warwick（沃里克大学） ； School of Engineering and Materials Science（工程与材料科学学校） ； Queen Mary University of London（伦敦女王学院） 纠错

专题命中 安全评测 ：safety(abstract)

Comments 4 pages, 1 figure

Semantic-guided Fine-tuning of Foundation Model for Long-tailed Visual Recognition

Yufei Peng, Yonggang Zhang, Yiu-ming Cheung

专题命中 安全评测 ：alignment(abstract)

Watch, Listen, Understand, Mislead: Tri-modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluation

Sahid Hossain Mustakim, S M Jishanul Islam, Ummay Maria Muna, Montasir Chowdhury, Mohammed Jawwadul Islam, Sadia Ahmmed, Tashfia Sikder, Syed Tasdid Azam Dhrubo, Swakkhar Shatabda

机构 * United International University（国际大学） ； BRAC University（BRAC大学） ； University of British Columbia（不列颠哥伦比亚大学） ； Bangladesh University of Professionals（孟加拉专业大学） ； University of Alberta（阿尔伯塔大学） 纠错

专题命中 安全评测 ：safety(abstract)

Comments Accepted as long paper, SVU Workshop at ICCV 2025

Text-Visual Semantic Constrained AI-Generated Image Quality Assessment

Qiang Li, Qingsen Yan, Haojian Huang, Peng Wu, Haokui Zhang, Yanning Zhang

机构 * Northwestern Polytechnical University（西北工业大学） ； The University of Hong Kong（香港大学） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments 9 pages, 5 figures, Accepted at ACMMM 2025

DRISHTIKON: Visual Grounding at Multiple Granularities in Documents

Badri Vishal Kasuba, Parag Chaudhuri, Ganesh Ramakrishnan

专题命中 安全评测 ：alignment(abstract)

Comments Work in Progress

OpenLKA: An Open Dataset of Lane Keeping Assist from Recent Car Models under Real-world Driving Conditions

Yuhang Wang, Abdulaziz Alhuraish, Shengming Yuan, Hao Zhou

机构 * Department of Civil and Environmental Engineering, University of South Florida（土木与环境工程系，佛罗里达州立大学） 纠错

专题命中 安全评测 ：safety(abstract)

LLMATCH: A Unified Schema Matching Framework with Large Language Models

Sha Wang, Yuchen Li, Hanhua Xiao, Bing Tian Dai, Roy Ka-Wei Lee, Yanfei Dong, Lambert Deng

专题命中 安全评测 ：alignment(abstract)

Comments Accepted at APWeb 2025, Schema Matching, LLM, Data Management

Quantum-Annealing Enhanced Machine Learning for Interpretable Phase Classification of High-Entropy Alloys

Diego Ibarra Hoyos, Gia-Wei Chern, Israel Klich, Joseph Poon

专题命中 安全评测 ：alignment(abstract)

Reconstruction of cosmic-ray properties with GNN in GRAND

Arsène Ferrière, Aurélien Benoit-Lévy

专题命中 安全评测 ：trustworthy(abstract)

Comments Presented at the 39th International Cosmic Ray Conference (ICRC 2025). 8 pages, 6 figures

Position Paper: Programming Language Techniques for Bridging LLM Code Generation Semantic Gaps

Yalong Du, Chaozheng Wang, Huaijin Wang

专题命中 安全评测 ：trustworthy(abstract)

LLM-enhanced Action-aware Multi-modal Prompt Tuning for Image-Text Matching

Mengxiao Tian, Xinxiao Wu, Shuo Yang

机构 * Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, China（北京智能信息技术重点实验室，计算机科学与技术学院，北京理工大学，中国） ； Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University, China（广东机器感知与智能计算实验室，深圳MSU-BIT大学，中国） ； Beijing Research Center of Intelligent Equipment for Agriculture, China（北京智能农业设备研究中心，中国） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments accepted by ICCV 2025

OnlineBEV: Recurrent Temporal Fusion in Bird's Eye View Representations for Multi-Camera 3D Perception

Junho Koh, Youngwoo Lee, Jungho Kim, Dongyoung Lee, Jun Won Choi

机构 * Autonomous Driving Development Center, Hyundai Motors（韩世汽车自动驾驶开发中心） ； Department of Electrical Engineering, Hanyang University（翰阳大学电气工程系） ； Interdisciplinary Program in Artificial Intelligence, Seoul National University（首尔国立大学人工智能跨学科项目） ； Department of Electrical and Computer Engineering, Seoul National University（首尔国立大学电气与计算机工程系） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments Accepted to Transactions on Intelligent Transportation Systems

BayesTTA: Continual-Temporal Test-Time Adaptation for Vision-Language Models via Gaussian Discriminant Analysis

Shuang Cui, Jinglin Xu, Yi Li, Xiongxin Tang, Jiangmeng Li, Jiahuan Zhou, Fanjiang Xu, Fuchun Sun, Hui Xiong

机构 * National Key Laboratory of Space Integrated Information System（国家空间信息集成系统重点实验室） ； Institute of Software Chinese Academy of Sciences（中国科学院软件研究所） ； University of Chinese Academy of Sciences（中国科学院大学） ； Wangxuan Institute of Computer Technology（计算机技术王轩研究所） ； Peking University（北京大学） ； Department of Computer Science and Technology（计算机科学与技术系） ； Tsinghua University（清华大学） ； Thrust of Artificial Intelligence, the Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）人工智能方向） ； Department of Computer Science & Engineering, the Hong Kong University of Science and Technology（香港科技大学计算机科学与工程系） 纠错

专题命中 安全评测 ：alignment(abstract)

Cycle Context Verification for In-Context Medical Image Segmentation

Shishuai Hu, Zehui Liao, Liangli Zhen, Huazhu Fu, Yong Xia

机构 * National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science ； Engineering, Northwestern Polytechnical University, Xi’an 710072, China Institute of High Performance Computing, Agency for Science, Technology ； Research, Singapore 138632, Singapore Ningbo Institute of Northwestern Polytechnical University, Ningbo 315048, China Research \& Development Institute of Northwestern Polytechnical University in Shenzhen, Shenzhen 518057, China 纠错

专题命中 安全评测 ：alignment(abstract)

Comments MICCAI 2025

AI for NONMEM Coding in Pharmacometrics Research and Education: Shortcut or Pitfall?

Wenhao Zheng, Wanbing Wang, Carl M. J. Kirkpatrick, Cornelia B. Landersdorfer, Huaxiu Yao, Jiawei Zhou

专题命中 安全评测 ：alignment(abstract)

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models

Jiale Zhao, Xinyang Jiang, Junyao Gao, Yuhao Xue, Cairong Zhao

机构 * Tongji University（同济大学） ； Microsoft Research Asia（微软亚洲研究院） 纠错

专题命中 安全评测 ：alignment(abstract)

MagiC: Evaluating Multimodal Cognition Toward Grounded Visual Reasoning

Chengfei Wu, Ronald Seoh, Bingxuan Li, Liqiang Zhang, Fengrong Han, Dan Goldwasser

机构 * Purdue University（普渡大学） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； University of California Los Angeles（加州大学洛杉矶分校） ； University of Connecticut（康涅狄格大学） ； University of California Berkeley（加州大学伯克利分校） 纠错

专题命中 安全评测 ：alignment(abstract)

Evaluating Attribute Confusion in Fashion Text-to-Image Generation

Ziyue Liu, Federico Girella, Yiming Wang, Davide Talon

机构 * University of Verona（威尼斯大学） ； Polytechnic University of Turin（都灵理工大学） ； Fondazione Bruno Kessler（布鲁诺·科塞勒基金会） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments Accepted to ICIAP25. Project page: site [https://intelligolabs.github.io/L-VQAScore/\

Dataset and Benchmark for Enhancing Critical Retained Foreign Object Detection

Yuli Wang, Victoria R. Shi, Liwei Zhou, Richard Chin, Yuwei Dai, Yuanyun Hu, Cheng-Yi Li, Haoyue Guan, Jiashu Cheng, Yu Sun, Cheng Ting Lin, Ihab Kamel, Premal Trivedi, Pamela Johnson, John Eng, Harrison Bai

专题命中 安全评测 ：safety(abstract)

AI-Augmented Metamorphic Testing for Comprehensive Validation of Autonomous Vehicles

Tony Zhang, Burak Kantarci, Umair Siddique

机构 * School of Electrical Engineering and Computer Science（电气工程与计算机科学学院） ； reasonX Labs Inc.（reasonX实验室） 纠错

专题命中 安全评测 ：safety(abstract)

Comments 4 pages, 2 figures, Accepted to 1st International Workshop on Software Engineering for Autonomous Driving Systems (SE4ADS 2025) in 47th International Conference on Software Engineering (ICSE) 2025

Differential Attention for Multimodal Crisis Event Analysis

Nusrat Munia, Junfeng Zhu, Olfa Nasraoui, Abdullah-Al-Zubaer Imran

机构 * University of Kentucky（肯塔基大学） ； Kentucky Geological Survey（肯塔基地质调查局） ； University of Louisville（路易斯维尔大学） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments Presented at CVPRw 2025, MMFM3

MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding

Zhicheng Zhang, Wuyou Xia, Chenxi Zhao, Zhou Yan, Xiaoqiang Liu, Yongjie Zhu, Wenyu Qin, Pengfei Wan, Di Zhang, Jufeng Yang

机构 * VCIP \& TMCC \& DISSec, College of Computer Science, Nankai University ； Pengcheng Laboratory 纠错

专题命中 安全评测 ：alignment(abstract)

Comments ICML 2025 (Spotlight, Top 2.6%)

Unlearning the Noisy Correspondence Makes CLIP More Robust

Haochen Han, Alex Jinpeng Wang, Peijun Ye, Fangming Liu

机构 * Peng Cheng Laboratory（鹏城实验室） ； Central South University（中南大学） 纠错

专题命中 安全评测 ：alignment(abstract)

Comments ICCV 2025