Automated driving has the potential to revolutionize personal, public, and freight mobility. Beside accurately perceiving the environment, automated vehicles must plan a safe, comfortable, and efficient motion trajectory. To promote safety and progress, many works rely on modules that predict the future motion of surrounding traffic. Modular automated driving systems commonly handle prediction and planning as sequential, separate tasks. While this accounts for the influence of surrounding traffic on the ego vehicle, it fails to anticipate the reactions of traffic participants to the ego vehicle's behavior. Recent methods increasingly integrate prediction and planning in a joint or interdependent step to model bidirectional interactions. To date, a comprehensive overview of different integration principles is lacking. We systematically review state-of-the-art deep learning-based planning systems, and focus on how they integrate prediction. Different facets of the integration ranging from system architecture to high-level behavioral aspects are considered and related to each other. Moreover, we discuss the implications, strengths, and limitations of different integration principles. By pointing out research gaps, describing relevant future challenges, and highlighting trends in the research field, we identify promising directions for future research.

Semantic segmentation is a crucial task in medical imaging. Although supervised learning techniques have proven to be effective in performing this task, they heavily depend on large amounts of annotated training data. The recently introduced Segment Anything Model (SAM) enables prompt-based segmentation and offers zero-shot generalization to unfamiliar objects. In our work, we leverage SAM's abstract object understanding for medical image segmentation to provide pseudo labels for semi-supervised learning, thereby mitigating the need for extensive annotated training data. Our approach refines initial segmentations that are derived from a limited amount of annotated data (comprising up to 43 cases) by extracting bounding boxes and seed points as prompts forwarded to SAM. Thus, it enables the generation of dense segmentation masks as pseudo labels for unlabelled data. The results show that training with our pseudo labels yields an improvement in Dice score from $74.29\,\%$ to $84.17\,\%$ and from $66.63\,\%$ to $74.87\,\%$ for the segmentation of bones of the paediatric wrist and teeth in dental radiographs, respectively. As a result, our method outperforms intensity-based post-processing methods, state-of-the-art supervised learning for segmentation (nnU-Net), and the semi-supervised mean teacher approach. Our Code is available on GitHub.

Principled reasoning about the identifiability of causal effects from non-experimental data is an important application of graphical causal models. This paper focuses on effects that are identifiable by covariate adjustment, a commonly used estimation approach. We present an algorithmic framework for efficiently testing, constructing, and enumerating $m$-separators in ancestral graphs (AGs), a class of graphical causal models that can represent uncertainty about the presence of latent confounders. Furthermore, we prove a reduction from causal effect identification by covariate adjustment to $m$-separation in a subgraph for directed acyclic graphs (DAGs) and maximal ancestral graphs (MAGs). Jointly, these results yield constructive criteria that characterize all adjustment sets as well as all minimal and minimum adjustment sets for identification of a desired causal effect with multivariate exposures and outcomes in the presence of latent confounding. Our results extend several existing solutions for special cases of these problems. Our efficient algorithms allowed us to empirically quantify the identifiability gap between covariate adjustment and the do-calculus in random DAGs and MAGs, covering a wide range of scenarios. Implementations of our algorithms are provided in the R package dagitty.

Machine learning is expected to fuel significant improvements in medical care. To ensure that fundamental principles such as beneficence, respect for human autonomy, prevention of harm, justice, privacy, and transparency are respected, medical machine learning systems must be developed responsibly. Many high-level declarations of ethical principles have been put forth for this purpose, but there is a severe lack of technical guidelines explicating the practical consequences for medical machine learning. Similarly, there is currently considerable uncertainty regarding the exact regulatory requirements placed upon medical machine learning systems. This survey provides an overview of the technical and procedural challenges involved in creating medical machine learning systems responsibly and in conformity with existing regulations, as well as possible solutions to address these challenges. First, a brief review of existing regulations affecting medical machine learning is provided, showing that properties such as safety, robustness, reliability, privacy, security, transparency, explainability, and nondiscrimination are all demanded already by existing law and regulations - albeit, in many cases, to an uncertain degree. Next, the key technical obstacles to achieving these desirable properties are discussed, as well as important techniques to overcome these obstacles in the medical context. We notice that distribution shift, spurious correlations, model underspecification, uncertainty quantification, and data scarcity represent severe challenges in the medical context. Promising solution approaches include the use of large and representative datasets and federated learning as a means to that end, the careful exploitation of domain knowledge, the use of inherently transparent models, comprehensive out-of-distribution model testing and verification, as well as algorithmic impact assessments.

Motion artifacts in Magnetic Resonance Imaging (MRI) arise due to relatively long acquisition times and can compromise the clinical utility of acquired images. Traditional motion correction methods often fail to address severe motion, leading to distorted and unreliable results. Deep Learning (DL) alleviated such pitfalls through generalization with the cost of vanishing structures and hallucinations, making it challenging to apply in the medical field where hallucinated structures can tremendously impact the diagnostic outcome. In this work, we present an instance-wise motion correction pipeline that leverages motion-guided Implicit Neural Representations (INRs) to mitigate the impact of motion artifacts while retaining anatomical structure. Our method is evaluated using the NYU fastMRI dataset with different degrees of simulated motion severity. For the correction alone, we can improve over state-of-the-art image reconstruction methods by $+5\%$ SSIM, $+5\:db$ PSNR, and $+14\%$ HaarPSI. Clinical relevance is demonstrated by a subsequent experiment, where our method improves classification outcomes by at least $+1.5$ accuracy percentage points compared to motion-corrupted images.

This paper presents a novel approach to recurrent neural network (RNN) regularization. Differently from the widely adopted dropout method, which is applied to \textit{forward} connections of feed-forward architectures or RNNs, we propose to drop neurons directly in \textit{recurrent} connections in a way that does not cause loss of long-term memory. Our approach is as easy to implement and apply as the regular feed-forward dropout and we demonstrate its effectiveness for Long Short-Term Memory network, the most popular type of RNN cells. Our experiments on NLP benchmarks show consistent improvements even when combined with conventional feed-forward dropout.

Optical coherence tomography (OCT) applications like ultra-widefield and full eye-length imaging are of high interest for various diagnostic purposes. In swept-source OCT these techniques require a swept light source, which is coherent over the whole imaging depth. We present a zero roll-off 1060 nm Fourier Domain Mode Locked-Laser (FDML-Laser) for retinal OCT imaging at 1.7 MHz A-scan rate and first long-range imaging results with it. Several steps such as improved dispersion compensation and frequency regulation were performed and will be discussed. Besides virtually no loss in OCT signal over the maximum depth range of 4.6 mm and very good dynamic range was observed. Roll-off measurements show no decrease of the point-spread function (PSF), while maintaining a high dynamic range.

The adoption of machine learning solutions is rapidly increasing across all parts of society. As the models grow larger, both training and inference of machine learning models is increasingly outsourced, e.g. to cloud service providers. This means that potentially sensitive data is processed on untrusted platforms, which bears inherent data security and privacy risks. In this work, we investigate how to protect distributed machine learning systems, focusing on deep convolutional neural networks. The most common and best-performing mixed MPC approaches are based on HE, secret sharing, and garbled circuits. They commonly suffer from large performance overheads, big accuracy losses, and communication overheads that grow linearly in the depth of the neural network. To improve on these problems, we present Dash, a fast and distributed private convolutional neural network inference scheme secure against malicious attackers. Building on arithmetic garbling gadgets [BMR16] and fancy-garbling [BCM+19], Dash is based purely on arithmetic garbled circuits. We introduce LabelTensors that allow us to leverage the massive parallelity of modern GPUs. Combined with state-of-the-art garbling optimizations, Dash outperforms previous garbling approaches up to a factor of about 100. Furthermore, we introduce an efficient scaling operation over the residues of the Chinese remainder theorem representation to arithmetic garbled circuits, which allows us to garble larger networks and achieve much higher accuracy than previous approaches. Finally, Dash requires only a single communication round per inference step, regardless of the depth of the neural network, and a very small constant online communication volume.

Microarchitectural side channels expose unprotected software to information leakage attacks where a software adversary is able to track runtime behavior of a benign process and steal secrets such as cryptographic keys. As suggested by incremental software patches for the RSA algorithm against variants of side-channel attacks within different versions of cryptographic libraries, protecting security-critical algorithms against side channels is an intricate task. Software protections avoid leakages by operating in constant time with a uniform resource usage pattern independent of the processed secret. In this respect, automated testing and verification of software binaries for leakage-free behavior is of importance, particularly when the source code is not available. In this work, we propose a novel technique based on Dynamic Binary Instrumentation and Mutual Information Analysis to efficiently locate and quantify memory based and control-flow based microarchitectural leakages. We develop a software framework named \tool~for side-channel analysis of binaries which can be extended to support new classes of leakage. For the first time, by utilizing \tool, we perform rigorous leakage analysis of two widely-used closed-source cryptographic libraries: \emph{Intel IPP} and \emph{Microsoft CNG}. We analyze $15$ different cryptographic implementations consisting of $112$ million instructions in about $105$ minutes of CPU time. By locating previously unknown leakages in hardened implementations, our results suggest that \tool~can efficiently find microarchitectural leakages in software binaries.

Microarchitectural side channel attacks have been very prominent in security research over the last few years. Caches have been an outstanding covert channel, as they provide high resolution and generic cross-core leakage even with simple user-mode code execution privileges. To prevent these generic cross-core attacks, all major cryptographic libraries now provide countermeasures to hinder key extraction via cross-core cache attacks, for instance avoiding secret dependent access patterns and prefetching data. In this paper, we show that implementations protected by 'good-enough' countermeasures aimed at preventing simple cache attacks are still vulnerable. We present a novel attack that uses a special timing technique to determine when an encryption has started and then evict the data precisely at the desired instant. This new attack does not require special privileges nor explicit synchronization between the attacker and the victim. One key improvement of our attack is a method to evict data from the cache with a single memory access and in absence of shared memory by leveraging the transient capabilities of TSX and relying on the recently reverse-engineered L3 replacement policy. We demonstrate the efficiency by performing an asynchronous last level cache attack to extract an RSA key from the latest wolfSSL library, which has been especially adapted to avoid leaky access patterns, and by extracting an AES key from the S-Box implementation included in OpenSSL bypassing the per round prefetch intended as a protection against cache attacks.

Modern Systems-on-Chip (SoCs) incorporate built-in self-test (BIST) modules deeply integrated into the device's intellectual property (IP) blocks. Such modules handle hardware faults and defects during device operation. As such, BIST results potentially reveal the internal structure and state of the device under test (DUT) and hence open attack vectors. So-called result compaction can overcome this vulnerability by hiding the BIST chain structure but introduces the issues of aliasing and invalid signatures. Software-BIST provides a flexible solution, that can tackle these issues, but suffers from limited observability and fault coverage. In this paper, we hence introduce a low-overhead software/hardware hybrid approach that overcomes the mentioned limitations. It relies on (a) keyed-hash message authentication code (KMAC) available on the SoC providing device-specific secure and valid signatures with zero aliasing and (b) the SoC processor for test scheduling hence increasing DUT availability. The proposed approach offers both on-chip- and remote-testing capabilities. We showcase a RISC-V-based SoC to demonstrate our approach, discussing system overhead and resulting compaction rates.

Integrating robots in complex everyday environments requires a multitude of problems to be solved. One crucial feature among those is to equip robots with a mechanism for teaching them a new task in an easy and natural way. When teaching tasks that involve sequences of different skills, with varying order and number of these skills, it is desirable to only demonstrate full task executions instead of all individual skills. For this purpose, we propose a novel approach that simultaneously learns to segment trajectories into reoccurring patterns and the skills to reconstruct these patterns from unlabelled demonstrations without further supervision. Moreover, the approach learns a skill conditioning that can be used to understand possible sequences of skills, a practical mechanism to be used in, for example, human-robot-interactions for a more intelligent and adaptive robot behaviour. The Bayesian and variational inference based approach is evaluated on synthetic and real human demonstrations with varying complexities and dimensionality, showing the successful learning of segmentations and skill libraries from unlabelled data.

Random survival forests (RSF) are a powerful method for risk prediction of right-censored outcomes in biomedical research. RSF use the log-rank split criterion to form an ensemble of survival trees. The most common approach to evaluate the prediction accuracy of a RSF model is Harrell's concordance index for survival data ('C index'). Conceptually, this strategy implies that the split criterion in RSF is different from the evaluation criterion of interest. This discrepancy can be overcome by using Harrell's C for both node splitting and evaluation. We compare the difference between the two split criteria analytically and in simulation studies with respect to the preference of more unbalanced splits, termed end-cut preference (ECP). Specifically, we show that the log-rank statistic has a stronger ECP compared to the C index. In simulation studies and with the help of two medical data sets we demonstrate that the accuracy of RSF predictions, as measured by Harrell's C, can be improved if the log-rank statistic is replaced by the C index for node splitting. This is especially true in situations where the censoring rate or the fraction of informative continuous predictor variables is high. Conversely, log-rank splitting is preferable in noisy scenarios. Both C-based and log-rank splitting are implemented in the R~package ranger. We recommend Harrell's C as split criterion for use in smaller scale clinical studies and the log-rank split criterion for use in large-scale 'omics' studies.

Current approaches for deformable medical image registration often struggle to fulfill all of the following criteria: versatile applicability, small computation or training times, and the being able to estimate large deformations. Furthermore, end-to-end networks for supervised training of registration often become overly complex and difficult to train. For the Learn2Reg2021 challenge, we aim to address these issues by decoupling feature learning and geometric alignment. First, we introduce a new very fast and accurate optimisation method. By using discretised displacements and a coupled convex optimisation procedure, we are able to robustly cope with large deformations. With the help of an Adam-based instance optimisation, we achieve very accurate registration performances and by using regularisation, we obtain smooth and plausible deformation fields. Second, to be versatile for different registration tasks, we extract hand-crafted features that are modality and contrast invariant and complement them with semantic features from a task-specific segmentation U-Net. With our results we were able to achieve the overall Learn2Reg2021 challenge's second place, winning Task 1 and being second and third in the other two tasks.

For the approximation of solutions for stochastic partial differential equations, numerical methods that obtain a high order of convergence and at the same time involve reasonable computational cost are of particular interest. We therefore propose a new numerical method of exponential stochastic Runge-Kutta type that allows for convergence with a temporal order of up to 3/2 and that can be combined with several spatial discretizations. The developed family of derivative-free schemes is tailored to stochastic partial differential equations of Nemytskii-type, i.e., with pointwise multiplicative noise operators. We prove the strong convergence of these schemes in the root mean-square sense and present some numerical examples that reveal the theoretical results.

The PI-CAI (Prostate Imaging: Cancer AI) challenge led to expert-level diagnostic algorithms for clinically significant prostate cancer detection. The algorithms receive biparametric MRI scans as input, which consist of T2-weighted and diffusion-weighted scans. These scans can be misaligned due to multiple factors in the scanning process. Image registration can alleviate this issue by predicting the deformation between the sequences. We investigate the effect of image registration on the diagnostic performance of AI-based prostate cancer diagnosis. First, the image registration algorithm, developed in MeVisLab, is analyzed using a dataset with paired lesion annotations. Second, the effect on diagnosis is evaluated by comparing case-level cancer diagnosis performance between using the original dataset, rigidly aligned diffusion-weighted scans, or deformably aligned diffusion-weighted scans. Rigid registration showed no improvement. Deformable registration demonstrated a substantial improvement in lesion overlap (+10% median Dice score) and a positive yet non-significant improvement in diagnostic performance (+0.3% AUROC, p=0.18). Our investigation shows that a substantial improvement in lesion alignment does not directly lead to a significant improvement in diagnostic performance. Qualitative analysis indicated that jointly developing image registration methods and diagnostic AI algorithms could enhance diagnostic accuracy and patient outcomes.

Autonomous robots need to interact with unknown, unstructured and changing environments, constantly facing novel challenges. Therefore, continuous online adaptation for lifelong-learning and the need of sample-efficient mechanisms to adapt to changes in the environment, the constraints, the tasks, or the robot itself are crucial. In this work, we propose a novel framework for probabilistic online motion planning with online adaptation based on a bio-inspired stochastic recurrent neural network. By using learning signals which mimic the intrinsic motivation signalcognitive dissonance in addition with a mental replay strategy to intensify experiences, the stochastic recurrent network can learn from few physical interactions and adapts to novel environments in seconds. We evaluate our online planning and adaptation framework on an anthropomorphic KUKA LWR arm. The rapid online adaptation is shown by learning unknown workspace constraints sample-efficiently from few physical interactions while following given way points.

This is a review on entropy in various fields of mathematics and science. Its scope is to convey a unified vision of the classical as well as some newer entropy notions to a broad audience with an intermediate background in dynamical systems and ergodic theory. Due to the breadth and depth of the subject, we have opted for a compact exposition whose contents are a compromise between conceptual import and instrumental relevance. The intended technical level and the space limitation born furthermore upon the final selection of the topics, which cover the three items named in the title. Specifically, the first part is devoted to the avatars of entropy in the traditional contexts: many particle physics, information theory, and dynamical systems. This chronological order helps to present the materials in a didactic manner. The axiomatic approach will be also considered at this stage to show that, quite remarkably, the essence of entropy can be encapsulated in a few basic properties. Inspired by the classical entropies, further akin quantities have been proposed in the course of time, mostly aimed at specific needs. A common denominator of those addressed in the second part of this review is their major impact on research. The final part shows that, along with its profound role in the theory, entropy has interesting practical applications beyond information theory and communications technology. For this sake we preferred examples from applied mathematics, although there are certainly nice applications in, say, physics, computer science and even social sciences. This review concludes with a representative list of references.

The satisfaction probability Pr[$\phi$] := Pr$_{\beta:vars(\phi) \to \{0,1\}}[\beta\models \phi]$of a propositional formula$\phi$ is the likelihood that a random assignment $\beta$ makes the formula true. We study the complexity of the problem $k$SAT-Pr_{&gt;p} = {$\phi$ is a $k$CNF formula | Pr[$\phi$] > p} for fixed $k$ and $p$. While 3SAT-Pr_{&gt;0} = 3SAT is NP-complete and SAT-Pr_{&gt;1/2} is PP-complete, Akmal and Williams recently showed that 3SAT-Pr_{&gt;1/2} lies in P and 4SAT-Pr_{&gt;1/2} is NP-complete; but the methods used to prove these striking results stay silent about, say, 4SAT-Pr_{&gt;3/4}, leaving the computational complexity of $k$SAT-Pr_{&gt;p} open for most $k$ and $p$. In the present paper we give a complete characterization in the form of a trichotomy: $k$SAT-Pr_{&gt;p} lies in AC$^0$, is NL-complete, or is NP-complete. The proof of the trichotomy hinges on a new order-theoretic insight: Every set of $k$CNF formulas contains a formula of maximum satisfaction probability. This deceptively simple statement allows us to (1) kernelize $k$SAT-Pr$_{\ge p}$ for the joint parameters $k$ and $p$, (2) show that the variables of the kernel form a backdoor set when the trichotomy states membership in AC$^0$ or NL, and (3) prove locality properties for $k$CNF formulas $\phi$, by which Pr[$\phi$] < $p$ implies that Pr[$\psi$] < $p$ holds already for a subset $\psi$ of $\phi$'s clauses whose size depends only on $k$ and $p$, and Pr[$\phi$] = $p$ implies $\phi \equiv \psi$ for some $k$CNF formula $\psi$ whose size once more depends only on $k$ and $p$.

We consider a higher-order Milstein scheme for stochastic partial differential equations with trace class noise which fulfill a certain commutativity condition. A novel technique to generally improve the order of convergence of Taylor schemes for stochastic partial differential equations is introduced. The key tool is an efficient approximation of the Milstein term by particularly tailored nested derivative-free terms. For the resulting derivative-free Milstein scheme the computational cost is, in general, considerably reduced by some power. Further, a rigorous computational cost model is considered and the so called effective order of convergence is introduced which allows to directly compare various numerical schemes in terms of their efficiency. As the main result, we prove for a broad class of stochastic partial differential equations, including equations with operators that do not need to be pointwise multiplicative, that the effective order of convergence of the proposed derivative-free Milstein scheme is significantly higher than for the original Milstein scheme. In this case, the derivative-free Milstein scheme outperforms the Euler scheme as well as the original Milstein scheme due to the reduction of the computational cost. Finally, we present some numerical examples that confirm the theoretical results.