- 综合排序
- 最热优先
- 最新优先
- 来自专栏Hongten
黑盒子测试方法(Black-Box Testing)
黑盒测试主要是根据产品的外部功能来规划测试，检查程序各个功能是否实现，主要的质量属性是否达到要求，其中有无错误。
1.4K20发布于 2018-09-13 - 来自专栏DeepHub IMBA
超参数黑盒（Black-box）优化的Python代码示例
暴力搜索优化的一个替代方案是黑盒（Black-Box）非凸优化技术。黑盒非凸优化算法可根据某些预定义的度量找到足够最佳的局部最小值（或最大值）的次优解。 Python具有许多这样的工具。
92910编辑于 2022-11-11 - 来自专栏MyBlog
Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Neural Networks论文笔记(1)
Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Neural Networks论文笔记 0. Goodfellow, “Transferability in Machine Learning: From Phenomena to Black-box Attacks using Adversarial Swami, “Practical Black-box Attacks Against Machine Learning,” in Asia Conference on Computer and Communications Bethge, “Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models Hsieh, “Zoo: Zeroth Order Optimization Based Black-box Attacks to Deep Neural Networks without Training
1.4K30发布于 2018-11-09 - 来自专栏MyBlog
Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Neural Networks 论文笔记(2)
该文章提出一种利用程序化噪声来生成对抗样本的方法, 所提出的方法和那些通过梯度不断修改以至于到达分类器的边界的方法不一样, 上述方法需要对目标的模型有一定的了解.
1.2K10发布于 2018-12-19 - 来自专栏AI科技评论
可学习的黑盒对抗攻击：SOTA的攻击成功率和查询效率
本文介绍NeurIPS 2020接收论文《Learning Black-Box Attackers with Transferable Priors and Query Feedback》。 ? 基于这一观察，我们提出了可学习的黑盒攻击方法（Learnable Black-Box Attack，LeBA）。目前，鲜有使用查询反馈来更新替代模型的研究。 Improving black-box adversarial attacks with a transfer-based prior. Simple Black-box Adversarial Attacks. ICML 2019. [4] Guo Y, Yan Z, Zhang C. Square attack: a query-efficient black-box adversarial attack via random search.
3.5K31发布于 2020-12-18 - 来自专栏专知
最新5篇生成对抗网络相关论文推荐—FusedGAN、DeblurGAN、AdvGAN、CipherGAN、MMD GANS
We apply AdvGAN in both semi-whitebox and black-box attack settings. In black-box attacks, we dynamically train a distilled model for the black-box model and optimize the Our attack has placed the first with 92.76% accuracy on a public MNIST black-box attack challenge. ?
1.9K70发布于 2018-04-13 - 来自专栏机器学习与生成对抗网络
ECCV 2020 的对抗相关论文（对抗生成、对抗攻击）
Segmentation Poster 2274 Adversarial Ranking Attack and Defense Poster 2336 Boosting Decision-based Black-box Adversarial Perturbations Using Context Inconsistency Poster 4362 Square Attack: a query-efficient black-box Bi-directional Likelihood Regularization for Visual Classification Poster 4889 Improving Query Efficiency of Black-box
71910发布于 2020-07-28 - 来自专栏算法和应用
基于LP松弛的客观稳健离散优化的黑盒削减问题
原文标题：Some Black-box Reductions for Objective-robust Discrete Optimization Problems Based on their LP-Relaxations
86120发布于 2019-07-18 - 来自专栏机器学习与推荐算法
KDD2022推荐系统论文集锦(附pdf下载)
Addressing Unmeasured Confounder for Recommendation with Sensitivity Analysis [6] Knowledge-enhanced Black-box to the security and privacy concerns, it is more practical to perform adversarial attacks under the black-box However, generating high-quality fake user profiles under black-box setting is rather challenging with More specifically, we propose a knowledge graph-enhanced black-box attacking framework (KGAttack) to integrated into hierarchical policy networks to generate fake user profiles for performing adversarial black-box
77320编辑于 2022-10-31 - 来自专栏深度学习进阶
AIOps根因定位（二）：微服务架构的异常检测与根因定位
a Service-Oriented Architecture. 4 基于监控指标的异常检测 4.1 异常检测 4.1.1 无监督检测 Detecting Anomalous Behavior of Black-Box FChain: Toward Black-Box Online Fault Localization for Cloud Systems. 4.2.2 基于拓扑图的分析 Graph-based root
4.7K43发布于 2021-09-15 - 来自专栏专知
CNN神经网络内部知识表达的“黑”与“白“
文题中的“黑”与“白”指的是神经网络的black-box的知识表达和我希望的white-box的可解释性模型。 作为博后研究员，我在UCLA带领几个学生探索一种语义层面可解释的神经网络特征表达，或者把black-box网络特征表达转化成white-box图模型。 ▌Disentangling CNN representations into graphical models ---- 其实在black-box表达中，之前提到的representation bias 但是让人尴尬的是，恰恰是神经网络black-box表达保证了特征提取的flexibility和信息表达的效率(见information bottleneck理论)。
94280发布于 2018-04-11 - 来自专栏有三AI
【每周CV论文推荐】基于GAN的对抗攻击，适合阅读那些文章入门？
Zoo: Zeroth order optimization based black-box attacks to deep neural networks without training substitute Decision-based adversarial attacks: Reliable attacks against black-box machine learning models[J]. arXiv
1.2K30编辑于 2022-11-07 - 来自专栏AI科技评论
北大 DAIR 实验室AutoML团队开源高效的通用黑盒优化系统OpenBox （KDD2021）
相关论文已经被KDD 2021录用，"OpenBox: A Generalized Black-box Optimization Service"。 "OpenBox: A Generalized Black-box Optimization Service." "Google vizier: A service for black-box optimization."
1.4K30发布于 2021-08-24 - 来自专栏AI算法与图像处理
论文速递2022.9.19！
2209.07923 代码/Code: https://github.com/BGU-CS-VIL/DeepMCBM A Large-scale Multiple-objective Method for Black-box
33920编辑于 2022-12-11 - 来自专栏接口测试
接口测试和功能测试的区别
Functionaltesting（功能测试），也称为behavioral testing（行为测试）、黑盒测试或数据驱动测试 黑盒测试（Black-box Testing，又称为功能测试或数据驱动测试
3K30发布于 2020-11-26 - 来自专栏机器之心
强化学习成帮凶，对抗攻击LLM有了新方法
近日，威斯康星大学麦迪逊分校的一个研究团队发现，可以通过强化学习对模型实施有效的黑盒逃避攻击（Black-Box Evasion Attacks）。 论文标题：Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning 论文地址：https://arxiv.org
28810编辑于 2025-03-07 - 来自专栏AI算法与图像处理
CVPR2022论文速递（2022.4.4）！共13篇
2204.00367 代码/Code: https://github.com/lingyanruan/DRBNet Investigating Top-k White-Box and Transferable Black-box
59720编辑于 2022-05-19 - 来自专栏数据派THU
【干货书】Python强化学习算法:学习、理解和开发智能算法以应对人工智能挑战
TD3 Applications 9 Model-Based RL 10 Imitation Learning with the DAgger Algorithm 11 Understanding Black-Box
35330编辑于 2023-03-29 - 来自专栏AI算法与图像处理
STABLE Diffusion 权重公布! 注册可下载使用论文速递2022.8.25！
with Action Recognition Networks 论文/Paper: http://arxiv.org/pdf/2208.11650 代码/Code: None Unrestricted Black-box
1.2K30编辑于 2022-12-11 - 来自专栏MyBlog
暴力的黑盒对抗样本攻击 -- ZOO
介绍 这次来介绍一篇CCS Workshop 2017的工作，"ZOO: Zeroth Order Optimization Based Black-box Attacks to Deep Neural
1.9K50发布于 2021-04-09
腾讯云开发者
Copyright © 2013 - 2026 Tencent Cloud. All Rights Reserved. 腾讯云 版权所有
深圳市腾讯计算机系统有限公司 ICP备案/许可证号：粤B2-20090059 
粤公网安备44030502008569号
腾讯云计算（北京）有限责任公司 京ICP证150476号 | 京ICP备11018762号