Existing neural network-based autonomous systems are shown to be vulnerable against adversarial attacks, therefore sophisticated evaluation on their robustness is of great importance. However, evaluating the robustness only under the worst-case scenarios based on known attacks is not comprehensive, not to mention that some of them even rarely occur in the real world. In addition, the distribution of safety-critical data is usually multimodal, while most traditional attacks and evaluation methods focus on a single modality. To solve the above challenges, we propose a flow-based multimodal safety-critical scenario generator for evaluating decisionmaking algorithms. The proposed generative model is optimized with weighted likelihood maximization and a gradient-based sampling procedure is integrated to improve the sampling efficiency. The safety-critical scenarios are generated by querying the task algorithms and the log-likelihood of the generated scenarios is in proportion to the risk level. Experiments on a self-driving task demonstrate our advantages in terms of testing efficiency and multimodal modeling capability. We evaluate six Reinforcement Learning algorithms with our generated traffic scenarios and provide empirical conclusions about their robustness.
SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models
West China Biomedical Big Data Center, West China Hospital, SCU(西昌生物医学大数据中心、西昌医院、SCU);NTU;USTC;TeleAI, China Telecom(TeleAI、中国电信);BUPT;Tsinghua University(清华大学);HKUST(Guangzhou)(HKUST(广州))
Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction
Multimodal Art Projection Research Community(多模态艺术投影研究社区);Beijing University of Posts and Telecommunications(北京邮电大学);HKUST(香港科技大学);University of Waterloo(滑铁卢大学);Vector Institute(矢量研究所)
Does Unification Come at a Cost? Uni-SafeBench: A Safety Benchmark for Unified Multimodal Large Models
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Institute of Automation, Chinese Academy of Sciences (CASIA)(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)
Automating Steering for Safe Multimodal Large Language Models
Zhejiang University(浙江大学);Zhejiang University - Ant Group Joint Lab of Knowledge Graph(浙江大学-蚂蚁集团知识图谱联合实验室);National University of Singapore, NUS-NCS Joint Lab(新加坡国立大学NUS-NCS联合实验室)
Looking and Listening Inside and Outside: Multimodal Artificial Intelligence Systems for Driver Safety Assessment and Intelligent Vehicle Decision-Making
Machine Intelligence, Interaction, and Imagination (Mi3) Laboratory(机器智能、交互与想象实验室);Laboratory for Intelligent and Safe Automobiles (LISA)(智能与安全汽车实验室);Johns Hopkins University(约翰霍普金斯大学);Center for Medicinal Cannabis Research (CMCR)(医药大麻研究中心)
SaFeR-ToolKit: Structured Reasoning via Virtual Tool Calling for Multimodal Safety
Huazhong University of Science and Technology(华中科技大学);Beijing University of Posts and Telecommunications(北京邮电大学);West China Hospital, Sichuan University(四川大学华西医院);Nanyang Technological University(南洋理工大学)
Evaluating Multimodal LLMs for Inpatient Diagnosis: Real-World Performance, Safety, and Cost Across Ten Frontier Models
School of Computer Science and Applied Mathematics, University of the Witwatersrand(沃斯兰大学计算机科学与应用数学学院);Wits MIND Institute, University of the Witwatersrand(沃斯兰大学Wits MIND研究所);Grai Labs, Cape Town, South Africa(南非开普敦Grai实验室);Faculty of Health Sciences, University of the Witwatersrand(沃斯兰大学健康科学学院);South African Medical Research Council Vaccines and Infectious Diseases Analytics Research Unit, Faculty of Health Sciences, University of the Witwatersrand(南非医学研究委员会疫苗与传染病分析研究单位,沃斯兰大学健康科学学院)
Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary
The State Key Laboratory of Blockchain and Data Security(区块链与数据安全国家重点实验室);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(杭州高新技术区(滨江)区块链与数据安全研究院);Language and Machine Intelligence Department, Ant Group(蚂蚁集团语言与机器智能部门)