Learning Type Inference for Enhanced Dataflow Analysis

Statically analyzing dynamically-typed code is a challenging endeavor, as even seemingly trivial tasks such as determining the targets of procedure calls are non-trivial without knowing the types of objects at compile time. Addressing this challenge, gradual typing is increasingly added to dynamically-typed languages, a prominent example being TypeScript that introduces static typing to JavaScript. Gradual typing improves the developer's ability to verify program behavior, contributing to robust, secure and debuggable programs. In practice, however, users only sparsely annotate types directly. At the same time, conventional type inference faces performance-related challenges as program size grows. Statistical techniques based on machine learning offer faster inference, but although recent approaches demonstrate overall improved accuracy, they still perform significantly worse on user-defined types than on the most common built-in types. Limiting their real-world usefulness even more, they rarely integrate with user-facing applications. We propose CodeTIDAL5, a Transformer-based model trained to reliably predict type annotations. For effective result retrieval and re-integration, we extract usage slices from a program's code property graph. Comparing our approach against recent neural type inference systems, our model outperforms the current state-of-the-art by 7.85% on the ManyTypes4TypeScript benchmark, achieving 71.27% accuracy overall. Furthermore, we present JoernTI, an integration of our approach into Joern, an open source static analysis tool, and demonstrate that the analysis benefits from the additional type information. As our model allows for fast inference times even on commodity CPUs, making our system available through Joern leads to high accessibility and facilitates security research.

Recovering from Privacy-Preserving Masking with Large Language Models

Model adaptation is crucial to handle the discrepancy between proxy training data and actual users data received. To effectively perform adaptation, textual data of users is typically stored on servers or their local devices, where downstream natural language processing (NLP) models can be directly trained using such in-domain data. However, this might raise privacy and security concerns due to the extra risks of exposing user information to adversaries. Replacing identifying information in textual data with a generic marker has been recently explored. In this work, we leverage large language models (LLMs) to suggest substitutes of masked tokens and have their effectiveness evaluated on downstream language modeling tasks. Specifically, we propose multiple pre-trained and fine-tuned LLM-based approaches and perform empirical studies on various datasets for the comparison of these methods. Experimental results show that models trained on the obfuscation corpora are able to achieve comparable performance with the ones trained on the original data without privacy-preserving token masking.

GelSight Svelte: A Human Finger-shaped Single-camera Tactile Robot Finger with Large Sensing Coverage and Proprioceptive Sensing

Camera-based tactile sensing is a low-cost, popular approach to obtain highly detailed contact geometry information. However, most existing camera-based tactile sensors are fingertip sensors, and longer fingers often require extraneous elements to obtain an extended sensing area similar to the full length of a human finger. Moreover, existing methods to estimate proprioceptive information such as total forces and torques applied on the finger from camera-based tactile sensors are not effective when the contact geometry is complex. We introduce GelSight Svelte, a curved, human finger-sized, single-camera tactile sensor that is capable of both tactile and proprioceptive sensing over a large area. GelSight Svelte uses curved mirrors to achieve the desired shape and sensing coverage. Proprioceptive information, such as the total bending and twisting torques applied on the finger, is reflected as deformations on the flexible backbone of GelSight Svelte, which are also captured by the camera. We train a convolutional neural network to estimate the bending and twisting torques from the captured images. We conduct gel deformation experiments at various locations of the finger to evaluate the tactile sensing capability and proprioceptive sensing accuracy. To demonstrate the capability and potential uses of GelSight Svelte, we conduct an object holding task with three different grasping modes that utilize different areas of the finger. More information is available on our website: https://gelsight-svelte.alanz.info

Using AI Uncertainty Quantification to Improve Human Decision-Making

AI Uncertainty Quantification (UQ) has the potential to improve human decision-making beyond AI predictions alone by providing additional useful probabilistic information to users. The majority of past research on AI and human decision-making has concentrated on model explainability and interpretability. We implemented instance-based UQ for three real datasets. To achieve this, we trained different AI models for classification for each dataset, and used random samples generated around the neighborhood of the given instance to create confidence intervals for UQ. The computed UQ was calibrated using a strictly proper scoring rule as a form of quality assurance for UQ. We then conducted two preregistered online behavioral experiments that compared objective human decision-making performance under different AI information conditions, including UQ. In Experiment 1, we compared decision-making for no AI (control), AI prediction alone, and AI prediction with a visualization of UQ. We found UQ significantly improved decision-making beyond the other two conditions. In Experiment 2, we focused on comparing different representations of UQ information: Point vs. distribution of uncertainty and visualization type (needle vs. dotplot). We did not find meaningful differences in decision-making performance among these different representations of UQ. Overall, our results indicate that human decision-making can be improved by providing UQ information along with AI predictions, and that this benefit generalizes across a variety of representations of UQ.

Joint RIS Phase Profile Design and Power Allocation for Parameter Estimation in Presence of Eavesdropping

We consider secure transmission of a deterministic complex-valued parameter vector from a transmitter to an intended receiver in the presence of an eavesdropper in a reconfigurable intelligent surface (RIS)-integrated environment. We aim to jointly optimize the RIS phase profile and the power allocation matrix at the transmitter to enhance the estimation accuracy at the intended receiver while limiting that at the eavesdropper. We utilize the trace of the Fisher information matrix (FIM), equivalently, the average Fisher information, as the estimation accuracy metric, and obtain its closed form expression for the intended receiver and the eavesdropper. Accordingly, the joint RIS phase profile and power allocation problem is formulated, and it is solved via alternating optimization. When the power allocation matrix is fixed during alternating optimization, the optimal RIS phase profile design problem is formulated as a non-convex problem and it is solved via semidefinite relaxation and rank reduction. When the RIS phase profile is fixed, a linear programming formulation is obtained for optimal power allocation. Via simulations, the effects of RIS phase design and power allocation are illustrated individually and jointly. Moreover, extensions are provided by considering the presence of line of sight paths in the environment and the availability of RIS elements with adjustable magnitudes.

Unsupervised correspondence with combined geometric learning and imaging for radiotherapy applications

The aim of this study was to develop a model to accurately identify corresponding points between organ segmentations of different patients for radiotherapy applications. A model for simultaneous correspondence and interpolation estimation in 3D shapes was trained with head and neck organ segmentations from planning CT scans. We then extended the original model to incorporate imaging information using two approaches: 1) extracting features directly from image patches, and 2) including the mean square error between patches as part of the loss function. The correspondence and interpolation performance were evaluated using the geodesic error, chamfer distance and conformal distortion metrics, as well as distances between anatomical landmarks. Each of the models produced significantly better correspondences than the baseline non-rigid registration approach. The original model performed similarly to the model with direct inclusion of image features. The best performing model configuration incorporated imaging information as part of the loss function which produced more anatomically plausible correspondences. We will use the best performing model to identify corresponding anatomical points on organs to improve spatial normalisation, an important step in outcome modelling, or as an initialisation for anatomically informed registrations. All our code is publicly available at https://github.com/rrr-uom-projects/Unsup-RT-Corr-Net

Morphological Computing as Logic Underlying Cognition in Human, Animal, and Intelligent Machine

This work examines the interconnections between logic, epistemology, and sciences within the Naturalist tradition. It presents a scheme that connects logic, mathematics, physics, chemistry, biology, and cognition, emphasizing scale-invariant, self-organizing dynamics across organizational tiers of nature. The inherent logic of agency exists in natural processes at various levels, under information exchanges. It applies to humans, animals, and artifactual agents. The common human-centric, natural language-based logic is an example of complex logic evolved by living organisms that already appears in the simplest form at the level of basal cognition of unicellular organisms. Thus, cognitive logic stems from the evolution of physical, chemical, and biological logic. In a computing nature framework with a self-organizing agency, innovative computational frameworks grounded in morphological/physical/natural computation can be used to explain the genesis of human-centered logic through the steps of naturalized logical processes at lower levels of organization. The Extended Evolutionary Synthesis of living agents is essential for understanding the emergence of human-level logic and the relationship between logic and information processing/computational epistemology. We conclude that more research is needed to elucidate the details of the mechanisms linking natural phenomena with the logic of agency in nature.

Black-box Attacks on Image Activity Prediction and its Natural Language Explanations

Explainable AI (XAI) methods aim to describe the decision process of deep neural networks. Early XAI methods produced visual explanations, whereas more recent techniques generate multimodal explanations that include textual information and visual representations. Visual XAI methods have been shown to be vulnerable to white-box and gray-box adversarial attacks, with an attacker having full or partial knowledge of and access to the target system. As the vulnerabilities of multimodal XAI models have not been examined, in this paper we assess for the first time the robustness to black-box attacks of the natural language explanations generated by a self-rationalizing image-based activity recognition model. We generate unrestricted, spatially variant perturbations that disrupt the association between the predictions and the corresponding explanations to mislead the model into generating unfaithful explanations. We show that we can create adversarial images that manipulate the explanations of an activity recognition model by having access only to its final output.

UPAR: A Kantian-Inspired Prompting Framework for Enhancing Large Language Model Capabilities

Large Language Models (LLMs) have demonstrated impressive inferential capabilities, with numerous research endeavors devoted to enhancing this capacity through prompting. Despite these efforts, a unified epistemological foundation is still conspicuously absent. Drawing inspiration from Kant's a priori philosophy, we propose the UPAR prompting framework, designed to emulate the structure of human cognition within LLMs. The UPAR framework is delineated into four phases: "Understand", "Plan", "Act", and "Reflect", enabling the extraction of structured information from complex contexts, prior planning of solutions, execution according to plan, and self-reflection. This structure significantly augments the explainability and accuracy of LLM inference, producing a human-understandable and inspectable inferential trajectory. Furthermore, our work offers an epistemological foundation for existing prompting techniques, allowing for a possible systematic integration of these methods. With GPT-4, our approach elevates the accuracy from COT baseline of 22.92% to 58.33% in a challenging subset of GSM8K, and from 67.91% to 75.40% in the causal judgment task.

Dual-Augmented Transformer Network for Weakly Supervised Semantic Segmentation

Weakly supervised semantic segmentation (WSSS), a fundamental computer vision task, which aims to segment out the object within only class-level labels. The traditional methods adopt the CNN-based network and utilize the class activation map (CAM) strategy to discover the object regions. However, such methods only focus on the most discriminative region of the object, resulting in incomplete segmentation. An alternative is to explore vision transformers (ViT) to encode the image to acquire the global semantic information. Yet, the lack of transductive bias to objects is a flaw of ViT. In this paper, we explore the dual-augmented transformer network with self-regularization constraints for WSSS. Specifically, we propose a dual network with both CNN-based and transformer networks for mutually complementary learning, where both networks augment the final output for enhancement. Massive systemic evaluations on the challenging PASCAL VOC 2012 benchmark demonstrate the effectiveness of our method, outperforming previous state-of-the-art methods.