Deep learning-based adversarial malware detectors have yielded promising results in detecting never-before-seen malware executables without relying on expensive dynamic behavior analysis and sandbox. Despite their abilities, these detectors have been shown to be vulnerable to adversarial malware variants - meticulously modified, functionality-preserving versions of original malware executables generated by machine learning. Due to the nature of these adversarial modifications, these adversarial methods often use a \textit{single view} of malware executables (i.e., the binary/hexadecimal view) to generate adversarial malware variants. This provides an opportunity for the defenders (i.e., malware detectors) to detect the adversarial variants by utilizing more than one view of a malware file (e.g., source code view in addition to the binary view). The rationale behind this idea is that while the adversary focuses on the binary view, certain characteristics of the malware file in the source code view remain untouched which leads to the detection of the adversarial malware variants. To capitalize on this opportunity, we propose Adversarially Robust Multiview Malware Defense (ARMD), a novel multi-view learning framework to improve the robustness of DL-based malware detectors against adversarial variants. Our experiments on three renowned open-source deep learning-based malware detectors across six common malware categories show that ARMD is able to improve the adversarial robustness by up to seven times on these malware detectors.
We introduce a new method to improve existing multilingual sentence embeddings with Abstract Meaning Representation (AMR). Compared with the original textual input, AMR is a structured semantic representation that presents the core concepts and relations in a sentence explicitly and unambiguously. It also helps reduce surface variations across different expressions and languages. Unlike most prior work that only evaluates the ability to measure semantic similarity, we present a thorough evaluation of existing multilingual sentence embeddings and our improved versions, which include a collection of five transfer tasks in different downstream applications. Experiment results show that retrofitting multilingual sentence embeddings with AMR leads to better state-of-the-art performance on both semantic textual similarity and transfer tasks. Our codebase and evaluation scripts can be found at \url{https://github.com/jcyk/MSE-AMR}.
Multi-modal 3D object detection has been an active research topic in autonomous driving. Nevertheless, it is non-trivial to explore the cross-modal feature fusion between sparse 3D points and dense 2D pixels. Recent approaches either fuse the image features with the point cloud features that are projected onto the 2D image plane or combine the sparse point cloud with dense image pixels. These fusion approaches often suffer from severe information loss, thus causing sub-optimal performance. To address these problems, we construct the homogeneous structure between the point cloud and images to avoid projective information loss by transforming the camera features into the LiDAR 3D space. In this paper, we propose a homogeneous multi-modal feature fusion and interaction method (HMFI) for 3D object detection. Specifically, we first design an image voxel lifter module (IVLM) to lift 2D image features into the 3D space and generate homogeneous image voxel features. Then, we fuse the voxelized point cloud features with the image features from different regions by introducing the self-attention based query fusion mechanism (QFM). Next, we propose a voxel feature interaction module (VFIM) to enforce the consistency of semantic information from identical objects in the homogeneous point cloud and image voxel representations, which can provide object-level alignment guidance for cross-modal feature fusion and strengthen the discriminative ability in complex backgrounds. We conduct extensive experiments on the KITTI and Waymo Open Dataset, and the proposed HMFI achieves better performance compared with the state-of-the-art multi-modal methods. Particularly, for the 3D detection of cyclist on the KITTI benchmark, HMFI surpasses all the published algorithms by a large margin.
Background: Medical images are more difficult to acquire and annotate than natural images, which results in data augmentation technologies often being used in medical image segmentation tasks. Most data augmentation technologies used in medical segmentation were originally developed on natural images and do not take into account the characteristic that the overall layout of medical images is standard and fixed. Methods: Based on the characteristics of medical images, we developed the cutting-splicing data augmentation (CS-DA) method, a novel data augmentation technology for medical image segmentation. CS-DA augments the dataset by splicing different position components cut from different original medical images into a new image. The characteristics of the medical image result in the new image having the same layout as and similar appearance to the original image. Compared with classical data augmentation technologies, CS-DA is simpler and more robust. Moreover, CS-DA does not introduce any noise or fake information into the newly created image. Results: To explore the properties of CS-DA, many experiments are conducted on eight diverse datasets. On the training dataset with the small sample size, CS-DA can effectively increase the performance of the segmentation model. When CS-DA is used together with classical data augmentation technologies, the performance of the segmentation model can be further improved and is much better than that of CS-DA and classical data augmentation separately. We also explored the influence of the number of components, the position of the cutting line, and the splicing method on the CS-DA performance. Conclusions: The excellent performance of CS-DA in the experiment has confirmed the effectiveness of CS-DA, and provides a new data augmentation idea for the small sample segmentation task.
Span Identification (SpanID) is a family of NLP tasks that aims to detect and classify text spans. Different from previous works that merely leverage Subordinate (\textsc{Sub}) relation about \textit{if a span is an instance of a certain category} to train SpanID models, we explore Peer (\textsc{Pr}) relation, which indicates that \textit{the two spans are two different instances from the same category sharing similar features}, and propose a novel \textbf{Peer} \textbf{D}ata \textbf{A}ugmentation (PeerDA) approach to treat span-span pairs with the \textsc{Pr} relation as a kind of augmented training data. PeerDA has two unique advantages: (1) There are a large number of span-span pairs with the \textsc{Pr} relation for augmenting the training data. (2) The augmented data can prevent over-fitting to the superficial span-category mapping by pushing SpanID models to leverage more on spans' semantics. Experimental results on ten datasets over four diverse SpanID tasks across seven domains demonstrate the effectiveness of PeerDA. Notably, seven of them achieve state-of-the-art results.
In this paper, we revisit the problem of computational modeling of simple and complex cells for an over-parameterized and direct-fit model of visual perception. Unlike conventional wisdom, we highlight the difference in parallel and sequential binding mechanisms between simple and complex cells. A new proposal for abstracting them into space partitioning and composition is developed as the foundation of our new hierarchical construction. Our construction can be interpreted as a product topology-based generalization of the existing k-d tree, making it suitable for brute-force direct-fit in a high-dimensional space. The constructed model has been applied to several classical experiments in neuroscience and psychology. We provide an anti-sparse coding interpretation of the constructed vision model and show how it leads to a dynamic programming (DP)-like approximate nearest-neighbor search based on $\ell_{\infty}$-optimization. We also briefly discuss two possible implementations based on asymmetrical (decoder matters more) auto-encoder and spiking neural networks (SNN), respectively.
Compared to visible-to-visible (V2V) person re-identification (ReID), the visible-to-infrared (V2I) person ReID task is more challenging due to the lack of sufficient training samples and the large cross-modality discrepancy. To this end, we propose Flow2Flow, a unified framework that could jointly achieve training sample expansion and cross-modality image generation for V2I person ReID. Specifically, Flow2Flow learns bijective transformations from both the visible image domain and the infrared domain to a shared isotropic Gaussian domain with an invertible visible flow-based generator and an infrared one, respectively. With Flow2Flow, we are able to generate pseudo training samples by the transformation from latent Gaussian noises to visible or infrared images, and generate cross-modality images by transformations from existing-modality images to latent Gaussian noises to missing-modality images. For the purpose of identity alignment and modality alignment of generated images, we develop adversarial training strategies to train Flow2Flow. Specifically, we design an image encoder and a modality discriminator for each modality. The image encoder encourages the generated images to be similar to real images of the same identity via identity adversarial training, and the modality discriminator makes the generated images modal-indistinguishable from real images via modality adversarial training. Experimental results on SYSU-MM01 and RegDB demonstrate that both training sample expansion and cross-modality image generation can significantly improve V2I ReID accuracy.
Object Re-IDentification (ReID), one of the most significant problems in biometrics and surveillance systems, has been extensively studied by image processing and computer vision communities in the past decades. Learning a robust and discriminative feature representation is a crucial challenge for object ReID. The problem is even more challenging in ReID based on Unmanned Aerial Vehicle (UAV) as the images are characterized by continuously varying camera parameters (e.g., view angle, altitude, etc.) of a flying drone. To address this challenge, multiscale feature representation has been considered to characterize images captured from UAV flying at different altitudes. In this work, we propose a multitask learning approach, which employs a new multiscale architecture without convolution, Pyramid Vision Transformer (PVT), as the backbone for UAV-based object ReID. By uncertainty modeling of intraclass variations, our proposed model can be jointly optimized using both uncertainty-aware object ID and camera ID information. Experimental results are reported on PRAI and VRAI, two ReID data sets from aerial surveillance, to verify the effectiveness of our proposed approach
This work tackles a central machine learning problem of performance degradation on out-of-distribution (OOD) test sets. The problem is particularly salient in medical imaging based diagnosis system that appears to be accurate but fails when tested in new hospitals/datasets. Recent studies indicate the system might learn shortcut and non-relevant features instead of generalizable features, so-called good features. We hypothesize that adversarial training can eliminate shortcut features whereas saliency guided training can filter out non-relevant features; both are nuisance features accounting for the performance degradation on OOD test sets. With that, we formulate a novel model training scheme for the deep neural network to learn good features for classification and/or detection tasks ensuring a consistent generalization performance on OOD test sets. The experimental results qualitatively and quantitatively demonstrate the superior performance of our method using the benchmark CXR image data sets on classification tasks.
For the Hamiltonian system, this work considers the learning and prediction of the position (q) and momentum (p) variables generated by a symplectic evolution map. Similar to Chen & Tao (2021), the symplectic map is represented by the generating function. In addition, we develop a new learning scheme by splitting the time series (q_i, p_i) into several partitions, and then train a leap-frog neural network (LFNN) to approximate the generating function between the first (i.e. initial condition) and one of the rest partitions. For predicting the system evolution in a short timescale, the LFNN could effectively avoid the issue of accumulative error. Then the LFNN is applied to learn the behavior of the 2:3 resonant Kuiper belt objects, in a much longer time period, and there are two significant improvements on the neural network constructed in our previous work (Li et al. 2022): (1) conservation of the Jacobi integral ; (2) highly accurate prediction of the orbital evolution. We propose that the LFNN may be useful to make the prediction of the long time evolution of the Hamiltonian system.