对于诸如银行和医疗保健等高度监管的行业，采用云计算的主要障碍之一是遵守监管标准。由于公司需要遵守的许多监管和技术规范（TechSpec）文件，这是一个复杂的问题。关键的问题是建立TechSpecs和法规控制之间的映射，以便从第一天开始，公司可以遵守最少的努力法规。我们证明了一种使用人工智能（AI）技术自动分析监管标准的方法的实用性。我们提出了早期的结果，以确定TechSpecs和监管控制之间的映射，并讨论该解决方案必须完全实用的挑战。

组织在云环境中努力处理纯粹的漏洞。用于优先考虑漏洞的事实方法是使用共同的漏洞评分系统（CVSS）。但是，CVSS具有固有的局限性，使其不理想优先级。在这项工作中，我们提出了一种优先考虑漏洞的新方法。我们的方法灵感来自进攻安全从业人员如何执行渗透测试。我们通过对大型客户进行现实世界案例研究评估我们的方法，以及机器学习的准确性，使过程端到端自动化。

现代组织为其网络和应用程序漏洞扫描仪发现和报告的漏洞数量奋斗。因此，优先级和专注力变得至关重要，将有限的时间花在最高风险漏洞上。为此，对于这些组织而言，重要的是要了解漏洞的技术描述，而且要了解攻击者的观点。在这项工作中，我们使用机器学习和自然语言处理技术，以及几个公开可用的数据集，以提供攻击技术和威胁参与者的漏洞的可解释映射。这项工作通过预测最有可能使用哪种攻击技术来利用给定的漏洞以及哪些威胁行为者最有可能进行剥削来提供新的安全情报。缺乏标记的数据和不同的词汇使映射漏洞以规模攻击技术一个具有挑战性的问题，使用监督或无监督的（相似性搜索）学习技术无法轻松解决。为了解决这个问题，我们首先将漏洞映射到一组标准的共同弱点，然后将攻击技术的共同弱点映射到一组弱点。该方法得出的平均相互等级（MRR）为0.95，这是一种准确性，与最新系统报告的准确性相当。我们的解决方案已部署到IBM Security X-Force Red漏洞管理服务，并在生产中进行。该解决方案帮助安全从业人员帮助客户管理和优先考虑其漏洞，从演员

Adversarial training is an effective approach to make deep neural networks robust against adversarial attacks. Recently, different adversarial training defenses are proposed that not only maintain a high clean accuracy but also show significant robustness against popular and well studied adversarial attacks such as PGD. High adversarial robustness can also arise if an attack fails to find adversarial gradient directions, a phenomenon known as `gradient masking'. In this work, we analyse the effect of label smoothing on adversarial training as one of the potential causes of gradient masking. We then develop a guided mechanism to avoid local minima during attack optimization, leading to a novel attack dubbed Guided Projected Gradient Attack (G-PGA). Our attack approach is based on a `match and deceive' loss that finds optimal adversarial directions through guidance from a surrogate model. Our modified attack does not require random restarts, large number of attack iterations or search for an optimal step-size. Furthermore, our proposed G-PGA is generic, thus it can be combined with an ensemble attack strategy as we demonstrate for the case of Auto-Attack, leading to efficiency and convergence speed improvements. More than an effective attack, G-PGA can be used as a diagnostic tool to reveal elusive robustness due to gradient masking in adversarial defenses.

Driving through pothole infested roads is a life hazard and economically costly. The experience is even worse for motorists using the pothole filled road for the first time. Pothole-filled road networks have been associated with severe traffic jam especially during peak times of the day. Besides not being fuel consumption friendly and being time wasting, traffic jams often lead to increased carbon emissions as well as noise pollution. Moreover, the risk of fatal accidents has also been strongly associated with potholes among other road network factors. Discovering potholes prior to using a particular road is therefore of significant importance. This work presents a successful demonstration of sensor-based pothole mapping agent that captures both the pothole's depth as well as its location coordinates, parameters that are then used to generate a pothole map for the agent's entire journey. The map can thus be shared with all motorists intending to use the same route.

Today's software is bloated leading to significant resource wastage. This bloat is prevalent across the entire software stack, from the operating system, all the way to software backends, frontends, and web-pages. In this paper, we study how prevalent bloat is in machine learning containers. We develop MMLB, a framework to analyze bloat in machine learning containers, measuring the amount of bloat that exists on the container and package levels. Our tool quantifies the sources of bloat and removes them. We integrate our tool with vulnerability analysis tools to measure how bloat affects container vulnerabilities. We experimentally study 15 machine learning containers from the official Tensorflow, Pytorch, and NVIDIA container registries under different tasks, (i.e., training, tuning, and serving). Our findings show that machine learning containers contain bloat encompassing up to 80\% of the container size. We find that debloating machine learning containers speeds provisioning times by up to $3.7\times$ and removes up to 98\% of all vulnerabilities detected by vulnerability analysis tools such as Grype. Finally, we relate our results to the larger discussion about technical debt in machine learning systems.

We consider the problem of improving the human instance segmentation mask quality for a given test image using keypoints estimation. We compare two alternative approaches. The first approach is a test-time adaptation (TTA) method, where we allow test-time modification of the segmentation network's weights using a single unlabeled test image. In this approach, we do not assume test-time access to the labeled source dataset. More specifically, our TTA method consists of using the keypoints estimates as pseudo labels and backpropagating them to adjust the backbone weights. The second approach is a training-time generalization (TTG) method, where we permit offline access to the labeled source dataset but not the test-time modification of weights. Furthermore, we do not assume the availability of any images from or knowledge about the target domain. Our TTG method consists of augmenting the backbone features with those generated by the keypoints head and feeding the aggregate vector to the mask head. Through a comprehensive set of ablations, we evaluate both approaches and identify several factors limiting the TTA gains. In particular, we show that in the absence of a significant domain shift, TTA may hurt and TTG show only a small gain in performance, whereas for a large domain shift, TTA gains are smaller and dependent on the heuristics used, while TTG gains are larger and robust to architectural choices.

Rating a video based on its content is an important step for classifying video age categories. Movie content rating and TV show rating are the two most common rating systems established by professional committees. However, manually reviewing and evaluating scene/film content by a committee is a tedious work and it becomes increasingly difficult with the ever-growing amount of online video content. As such, a desirable solution is to use computer vision based video content analysis techniques to automate the evaluation process. In this paper, related works are summarized for action recognition, multi-modal learning, movie genre classification, and sensitive content detection in the context of content moderation and movie content rating. The project page is available at https://github.com/fcakyon/content-moderation-deep-learning}.

Generalizable 3D part segmentation is important but challenging in vision and robotics. Training deep models via conventional supervised methods requires large-scale 3D datasets with fine-grained part annotations, which are costly to collect. This paper explores an alternative way for low-shot part segmentation of 3D point clouds by leveraging a pretrained image-language model, GLIP, which achieves superior performance on open-vocabulary 2D detection. We transfer the rich knowledge from 2D to 3D through GLIP-based part detection on point cloud rendering and a novel 2D-to-3D label lifting algorithm. We also utilize multi-view 3D priors and few-shot prompt tuning to boost performance significantly. Extensive evaluation on PartNet and PartNet-Mobility datasets shows that our method enables excellent zero-shot 3D part segmentation. Our few-shot version not only outperforms existing few-shot approaches by a large margin but also achieves highly competitive results compared to the fully supervised counterpart. Furthermore, we demonstrate that our method can be directly applied to iPhone-scanned point clouds without significant domain gaps.

Computational catalysis is playing an increasingly significant role in the design of catalysts across a wide range of applications. A common task for many computational methods is the need to accurately compute the minimum binding energy - the adsorption energy - for an adsorbate and a catalyst surface of interest. Traditionally, the identification of low energy adsorbate-surface configurations relies on heuristic methods and researcher intuition. As the desire to perform high-throughput screening increases, it becomes challenging to use heuristics and intuition alone. In this paper, we demonstrate machine learning potentials can be leveraged to identify low energy adsorbate-surface configurations more accurately and efficiently. Our algorithm provides a spectrum of trade-offs between accuracy and efficiency, with one balanced option finding the lowest energy configuration, within a 0.1 eV threshold, 86.63% of the time, while achieving a 1387x speedup in computation. To standardize benchmarking, we introduce the Open Catalyst Dense dataset containing nearly 1,000 diverse surfaces and 87,045 unique configurations.