Humans are universal decision makers: we reason causally to understand the world; we act competitively to gain advantage in commerce, games, and war; and we are able to learn to make better decisions through trial and error. In this paper, we propose Universal Decision Model (UDM), a mathematical formalism based on category theory. Decision objects in a UDM correspond to instances of decision tasks, ranging from causal models and dynamical systems such as Markov decision processes and predictive state representations, to network multiplayer games and Witsenhausen's intrinsic models, which generalizes all these previous formalisms. A UDM is a category of objects, which include decision objects, observation objects, and solution objects. Bisimulation morphisms map between decision objects that capture structure-preserving abstractions. We formulate universal properties of UDMs, including information integration, decision solvability, and hierarchical abstraction. We describe universal functorial representations of UDMs, and propose an algorithm for computing the minimal object in a UDM using algebraic topology. We sketch out an application of UDMs to causal inference in network economics, using a complex multiplayer producer-consumer two-sided marketplace.
MCTSteg: A Monte Carlo Tree Search-based Reinforcement Learning Framework for Universal Non-additive Steganography
College of Computer Science and Software Engineering, Shenzhen University(深圳大学计算机与软件学院);College of Information Engineering, Shenzhen University(深圳大学信息工程学院);Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)(广东省人工智能与数字经济实验室(深圳));Shenzhen Institute of Artificial Intelligence and Robotics for Society(深圳市人工智能与机器人研究院);Alibaba Group(阿里巴巴集团)
Consistent Attack: Universal Adversarial Perturbation on Embodied Vision Navigation
Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology, Tsinghua-Bosch Joint Center for Machine Learning, Institute for Artificial Intelligence, Tsinghua University, Beijing 100084, China(计算机科学与技术系,北京信息科学国家研究中心,清华-博世联合机器学习中心,人工智能研究院,清华大学,北京)
Towards a Universal Theory of Artificial Intelligence based on Algorithmic Probability and Sequential Decision Theory
决策理论正式解决了不确定世界中理性主体的问题,如果真实的环境概率分布是已知的。Solomonoff的泛归纳理论形式化地解决了未知分布的序列预测问题。我们统一了这两种理论,并给出了强有力的论据,由此产生的通用AIXI模型在任何可计算的环境中表现最佳。AIXI模型的主要缺点是它是不可计算的。为了克服这个问题,我们构造了一个改进的算法AIXI^tl,它仍然优于任何其他时间t和空间l有界代理。AIXI^tl的计算时间为t x 2^l的数量级。
University of California(加利福尼亚大学);Lawrence Livermore National Lab(劳伦斯利弗莫尔国家实验室)
我们研究了找到一个通用的(图像不可知的)扰动来欺骗机器学习(ML)分类器(例如,神经网络,决策树)在硬标签黑盒设置。白盒环境中对抗性ML的最新工作(模型参数已知)已经表明,许多最先进的图像分类器容易受到普遍对抗性扰动的影响:一种固定的人类无法感知的扰动,当添加到任何图像时,会导致其被错误分类的概率很高Kurakin et al.[2016],Szegedy et al. [2013],Chen et al. [2017 a],Carlini和Wagner [2017]。本文考虑了一个更实际和具有挑战性的问题,找到这样的普遍扰动在一个模糊的(或黑盒)设置。更具体地说,我们使用零阶优化算法来找到这样一个普遍的对抗扰动时,没有模型信息被揭示,除了攻击者可以进行查询,以探测分类。我们进一步放松的假设,查询的输出是连续值的置信度分数的所有类,并考虑输出是一个硬标签的决定的情况下。令人惊讶的是,我们发现,即使在这些极其模糊的制度中,最先进的ML分类器也可以通过向任何自然图像添加一个人类无法感知的图像扰动来以非常高的概率被愚弄。在硬标签黑盒设置中令人惊讶的普遍扰动的存在引起了严重的安全问题,因为存在一个普遍的噪声向量,对手可能会利用它来破坏大多数自然图像上的分类器。
Robustness of classifiers to universal perturbations: a geometric perspective
École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院);University of California, Los Angeles(加利福尼亚大学洛杉矶分校);ENS de Lyon(里昂高等师范学校);CNRS(法国国家科学研究中心);UCBL(里昂第一大学);INRIA(法国国家信息与自动化研究所);Université de Lyon(里昂大学)
ReCode: Unify Plan and Action for Universal Granularity Control
DeepWisdom;The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Renmin University of China(中国人民大学);Zhejiang University(浙江大学);Université de Montréal & Mila(蒙特利尔大学及Mila)
Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systems
Fudan University(复旦大学);East China Normal University(华东师范大学);Shanghai Innovation Institute(上海创新研究院);The University of Tokyo(东京大学);Macau University of Science and Technology(澳门科学理工学院);Concordia University(Concordia大学);University of Alberta(阿尔伯塔大学);The University of Tokyo, Japan(日本东京大学)