传感器对于机器人车辆（RV）中的自动操作至关重要。对传感器篡改或欺骗等传感器的物理攻击可以通过物理通道为RV提供错误的值，从而导致任务失败。在本文中，我们介绍了DeLorean，这是一个综合诊断和恢复框架，用于保护自动RV免受身体攻击。我们考虑了一种强烈的物理攻击形式，称为传感器欺骗攻击（SDA），其中对手同时靶向不同类型的多个传感器（甚至包括所有传感器）。在SDA下，Delorean检查攻击引起的错误，标识目标传感器，并防止错误的传感器输入在RV的反馈控制环中使用。 Delorean在反馈控制循环中重播历史性状态信息，并从攻击中恢复RV。我们对四个真实和两个模拟的RV的评估表明，DeLorean可以从不同的攻击中恢复RV，并确保在94％的情况下（平均）（平均而言）的任务成功，而不会发生任何崩溃。 Delorean会产生低性能，内存和电池开销。

对图像分类的侵扰贴片攻击攻击图像的深度神经网络（DNN），其在图像的有界区域内注射任意扭曲，可以产生鲁棒（IE在物理世界中的侵犯）和普遍（即，在任何情况下保持对抗的侵犯扰动输入）。这种攻击可能导致现实世界的DNN系统中的严重后果。这项工作提出了jujutsu，一种检测和减轻稳健和普遍的对抗性补丁攻击的技术。对于检测，jujutsu利用攻击“通用属性 - jujutsu首先定位潜在的对抗性补丁区域，然后策略性地将其传送到新图像中的专用区域，以确定它是否真正恶意。对于攻击缓解，jujutsu通过图像修正来利用攻击本地化性质，以在攻击损坏的像素中综合语义内容，并重建“清洁”图像。我们在四个不同的数据集中评估jujutsu（想象成，想象力，celeba和place365），并表明Jujutsu实现了卓越的性能，并且显着优于现有技术。我们发现jujutsu可以进一步防御基本攻击的不同变体，包括1）物理攻击; 2）目标不同课程的攻击; 3）攻击构造不同形状和4）适应攻击的修补程序。

Deep neural networks (DNN) are prone to miscalibrated predictions, often exhibiting a mismatch between the predicted output and the associated confidence scores. Contemporary model calibration techniques mitigate the problem of overconfident predictions by pushing down the confidence of the winning class while increasing the confidence of the remaining classes across all test samples. However, from a deployment perspective, an ideal model is desired to (i) generate well-calibrated predictions for high-confidence samples with predicted probability say >0.95, and (ii) generate a higher proportion of legitimate high-confidence samples. To this end, we propose a novel regularization technique that can be used with classification losses, leading to state-of-the-art calibrated predictions at test time; From a deployment standpoint in safety-critical applications, only high-confidence samples from a well-calibrated model are of interest, as the remaining samples have to undergo manual inspection. Predictive confidence reduction of these potentially ``high-confidence samples'' is a downside of existing calibration approaches. We mitigate this by proposing a dynamic train-time data pruning strategy that prunes low-confidence samples every few epochs, providing an increase in "confident yet calibrated samples". We demonstrate state-of-the-art calibration performance across image classification benchmarks, reducing training time without much compromise in accuracy. We provide insights into why our dynamic pruning strategy that prunes low-confidence training samples leads to an increase in high-confidence samples at test time.

Arbitrary pattern formation (\textsc{Apf}) is well studied problem in swarm robotics. The problem has been considered in two different settings so far; one is in plane and another is in infinite grid. This work deals the problem in infinite rectangular grid setting. The previous works in literature dealing with \textsc{Apf} problem in infinite grid had a fundamental issue. These deterministic algorithms use a lot space of the grid to solve the problem mainly because of maintaining asymmetry of the configuration or to avoid collision. These solution techniques can not be useful if there is a space constrain in the application field. In this work, we consider luminous robots (with one light that can take two colors) in order to avoid symmetry, but we carefully designed a deterministic algorithm which solves the \textsc{Apf} problem using minimal required space in the grid. The robots are autonomous, identical, anonymous and they operate in Look-Compute-Move cycles under a fully asynchronous scheduler. The \textsc{Apf} algorithm proposed in [WALCOM'2019] by Bose et al. can be modified using luminous robots so that it uses minimal space but that algorithm is not move optimal. The algorithm proposed in this paper not only uses minimal space but also asymptotically move optimal. The algorithm proposed in this work is designed for infinite rectangular grid but it can be easily modified to work in a finite grid as well.

This study concerns the formulation and application of Bayesian optimal experimental design to symbolic discovery, which is the inference from observational data of predictive models taking general functional forms. We apply constrained first-order methods to optimize an appropriate selection criterion, using Hamiltonian Monte Carlo to sample from the prior. A step for computing the predictive distribution, involving convolution, is computed via either numerical integration, or via fast transform methods.

Real-world tasks are largely composed of multiple models, each performing a sub-task in a larger chain of tasks, i.e., using the output from a model as input for another model in a multi-model pipeline. A model like MATRa performs the task of Crosslingual Transliteration in two stages, using English as an intermediate transliteration target when transliterating between two indic languages. We propose a novel distillation technique, EPIK, that condenses two-stage pipelines for hierarchical tasks into a single end-to-end model without compromising performance. This method can create end-to-end models for tasks without needing a dedicated end-to-end dataset, solving the data scarcity problem. The EPIK model has been distilled from the MATra model using this technique of knowledge distillation. The MATra model can perform crosslingual transliteration between 5 languages - English, Hindi, Tamil, Kannada and Bengali. The EPIK model executes the task of transliteration without any intermediate English output while retaining the performance and accuracy of the MATra model. The EPIK model can perform transliteration with an average CER score of 0.015 and average phonetic accuracy of 92.1%. In addition, the average time for execution has reduced by 54.3% as compared to the teacher model and has a similarity score of 97.5% with the teacher encoder. In a few cases, the EPIK model (student model) can outperform the MATra model (teacher model) even though it has been distilled from the MATra model.

We present XKD, a novel self-supervised framework to learn meaningful representations from unlabelled video clips. XKD is trained with two pseudo tasks. First, masked data reconstruction is performed to learn modality-specific representations. Next, self-supervised cross-modal knowledge distillation is performed between the two modalities through teacher-student setups to learn complementary information. To identify the most effective information to transfer and also to tackle the domain gap between audio and visual modalities which could hinder knowledge transfer, we introduce a domain alignment strategy for effective cross-modal distillation. Lastly, to develop a general-purpose solution capable of handling both audio and visual streams, a modality-agnostic variant of our proposed framework is introduced, which uses the same backbone for both audio and visual modalities. Our proposed cross-modal knowledge distillation improves linear evaluation top-1 accuracy of video action classification by 8.4% on UCF101, 8.1% on HMDB51, 13.8% on Kinetics-Sound, and 14.2% on Kinetics400. Additionally, our modality-agnostic variant shows promising results in developing a general-purpose network capable of handling different data streams. The code is released on the project website.

Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.

A machine learning model, under the influence of observed or unobserved confounders in the training data, can learn spurious correlations and fail to generalize when deployed. For image classifiers, augmenting a training dataset using counterfactual examples has been empirically shown to break spurious correlations. However, the counterfactual generation task itself becomes more difficult as the level of confounding increases. Existing methods for counterfactual generation under confounding consider a fixed set of interventions (e.g., texture, rotation) and are not flexible enough to capture diverse data-generating processes. Given a causal generative process, we formally characterize the adverse effects of confounding on any downstream tasks and show that the correlation between generative factors (attributes) can be used to quantitatively measure confounding between generative factors. To minimize such correlation, we propose a counterfactual generation method that learns to modify the value of any attribute in an image and generate new images given a set of observed attributes, even when the dataset is highly confounded. These counterfactual images are then used to regularize the downstream classifier such that the learned representations are the same across various generative factors conditioned on the class label. Our method is computationally efficient, simple to implement, and works well for any number of generative factors and confounding variables. Our experimental results on both synthetic (MNIST variants) and real-world (CelebA) datasets show the usefulness of our approach.

类比推理问题挑战了连接主义者和符号AI系统，因为这些系统需要将背景知识，推理和模式识别的结合。符号系统摄入显式域知识并执行演绎推理，但它们对噪声敏感，并且需要输入以预设符号特征。另一方面，Connectionist系统可以直接摄入丰富的输入空间，例如图像，文本或语音，即使使用嘈杂的输入也可以识别模式。但是，Connectionist模型努力将明确的领域知识用于演绎推理。在本文中，我们提出了一个框架，将神经网络的模式识别能力与象征性推理和背景知识结合在一起，以解决一类类似推理问题，其中一组属性和可能的​​关系是已知的。我们从“神经算法推理”方法[DeepMind 2020]中汲取灵感，并通过（i）基于问题的象征模型学习分布式表示（ii）培训神经网络转化反映了关系的分布式表示形式。参与问题，最后（iii）培训神经网络编码器，从图像到（i）中的分布式表示。这三个要素使我们能够使用神经网络作为操纵分布式表示的基本功能执行基于搜索的推理。我们在乌鸦渐进式矩阵中的视觉类比问题上进行了测试，并在人类绩效中实现准确性竞争，在某些情况下，优于初始端到端神经网络方法的方法。尽管最近接受大规模训练的神经模型产生了SOTA，但我们的新型神经符号推理方法是该问题的有希望的方向，可以说是更笼统的，尤其是对于可用的域知识的问题。