DeepGD: A Multi-Objective Black-Box Test Selection Approach for Deep Neural Networks
University of Ottawa（渥太华大学）；École de Technologie Supérieure（高等技术学院）；Lero SFI Centre on Software Research and University of Limerick（Lero SFI软件研究中心与利默里克大学）
Deep neural networks (DNNs) are widely used in various application domains such as image processing, speech recognition, and natural language processing. However, testing DNN models may be challenging due to the complexity and size of their input domain. Particularly, testing DNN models often requires generating or exploring large unlabeled datasets. In practice, DNN test oracles, which identify the correct outputs for inputs, often require expensive manual effort to label test data, possibly involving multiple experts to ensure labeling correctness. In this paper, we propose DeepGD, a black-box multi-objective test selection approach for DNN models. It reduces the cost of labeling by prioritizing the selection of test inputs with high fault revealing power from large unlabeled datasets. DeepGD not only selects test inputs with high uncertainty scores to trigger as many mispredicted inputs as possible but also maximizes the probability of revealing distinct faults in the DNN model by selecting diverse mispredicted inputs. The experimental results conducted on four widely used datasets and five DNN models show that in terms of fault-revealing ability: (1) White-box, coverage-based approaches fare poorly, (2) DeepGD outperforms existing black-box test selection approaches in terms of fault detection, and (3) DeepGD also leads to better guidance for DNN model retraining when using selected inputs to augment the training set.
Black-Box Optimization Revisited: Improving Algorithm Selection Wizards through Massive Benchmarking
Facebook AI Research（Facebook AI研究院）；The Chinese University of Hong Kong（香港中文大学）；Université Paris-Saclay（巴黎萨克雷大学）；Université Clermont Auvergne（克莱蒙奥弗涅大学）；Sorbonne Université（索邦大学）
Stabilizing black-box model selection with the inflated argmax
Data Science Institute, University of Chicago（芝加哥大学数据科学研究所）；Department of Statistics, University of Michigan（密歇根大学统计学系）；Department of Statistics, University of Chicago（芝加哥大学统计学系）；Department of Computer Science, University of Chicago（芝加哥大学计算机科学系）
WASHH: An Anchor-Aware Whale-Guided Selection Hyper-Heuristic for Continuous Optimization and SVC Configuration
Faculty of Applied Sciences, Macao Polytechnic University（澳门理工学院应用科学学院）；School of Mechanical and Electrical Engineering and Automation, Shanghai University（上海大学机械与自动化工程学院）；Pazhou Lab (Huangpu), Guangzhou（广州 Pazhou 实验室（黄埔））；College of Animal Science and Technology, Zhongkai University of Agriculture and Engineering（仲恺农业工程学院动物科学与技术学院）；Macao Polytechnic University（澳门理工学院）
In-Context Batch Black-box Optimization via Flow Matching
ELLIS Institute Finland（芬兰ELLIS研究所）；Department of Computer Science, Aalto University（阿尔托大学计算机系）；Department of Computer Science, University of Manchester（曼彻斯特大学计算机系）
Less is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算机与数据科学学院）；School of Artificial Intelligence, University of Science and Technology Beijing（北京科技大学人工智能学院）；Department of Mechanical Engineering, Imperial College London（伦敦帝国理工学院机械工程系）；Center for Machine Vision and Signal Analysis (CMVS), University of Oulu（奥卢大学机器视觉与信号分析中心）；School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区计算机科学与技术学院）
Robust Bayesian optimization with reinforcement learned acquisition functions
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Collaborative Innovation Center of Novel Software Technology and Industrialization（新型软件技术与产业化协同创新中心）；State Key Laboratory of Aerodynamics（空气动力学国家重点实验室）
DeepPySR -- A Symbolic Regression Framework with Dynamic Pruning, Pareto Selection, and Hierarchical Composition for Real-World Scientific Discovery
International Centre for Radio Astronomy Research (ICRAR), University of Western Australia（国际射电天文学研究中心（ICRAR），西澳大利亚大学）；The Raine Study, University of Western Australia（雷恩研究中心，西澳大利亚大学）；Menzies Institute for Medical Research, University of Tasmania（孟席斯医学研究所，塔斯马尼亚大学）；Nutrition & Health Innovation Research Institute, School of Medical and Health Sciences, Edith Cowan University（营养与健康创新研究所，伊迪斯科文大学医学与健康科学学院）
Enhancing ML Models Interpretability for Credit Scoring
Dept. of Computer Science, Delft University of Technology（代尔夫特理工大学计算机科学系）；Dept. of Applied Mathematics, Delft University of Technology（代尔夫特理工大学应用数学系）；FF Quant Advisory B.V.（FF量化咨询公司）
A Nested Weighted Tchebycheff Multi-Objective Bayesian Optimization Approach for Flexibility of Unknown Utopia Estimation in Expensive Black-box Design Problems
Oregon State University（俄勒冈州立大学）；Oak Ridge National Laboratory（橡树岭国家实验室）
DI-AA: An Interpretable White-box Attack for Fooling Deep Neural Networks
Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University（北京交通大学智能交通安全与隐私北京市重点实验室）；University of Zaragoza（萨拉戈萨大学）
A Survey of Features Used for Representing Black-box Single-objective Continuous Optimization
Computer Systems Department, Jožef Stefan Institute（乔塞夫·斯蒂芬研究所计算机系统系）；Jožef Stefan International Postgraduate School（乔塞夫·斯蒂芬国际研究生学院）；Leiden Institute for Advanced Computer Science（莱顿高级计算机科学研究所）；Computer Science department LIP6, Sorbonne Université, CNRS（索邦大学LIP6计算机科学系，CNRS）；Jožef Stefan Institute（乔塞夫·斯蒂芬研究所）
Interpreting Black Box Predictions using Fisher Kernels
University of California at Berkeley（加州大学伯克利分校）；Google Brain（谷歌大脑）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Automated Algorithm Selection for Radar Network Configuration
Thales Research & Technology（泰雷兹研究与技术公司）；École Polytechnique（巴黎综合理工学院）；Institut Polytechnique de Paris（巴黎理工学院）；Institut Pasteur（巴斯德研究所）；Université Paris Cité（巴黎西岱大学）；Thales Land & Air Systems（泰雷兹陆空系统公司）；Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）
