Title
Topic
-
‘ShadowNet: A Secure and Efficient On-Device Model Inference System for Convolutional Neural Networks’
“With the increased usage of AI accelerators on mobile and edge devices, on-device machine learning (ML) is gaining popularity. Thousands of proprietary ML models are being deployed today on billions of untrusted devices. This raises serious security concerns about model privacy. … In this paper, we present a novel on-device model inference system, ShadowNet. ShadowNet protects the model privacy with Trusted Execution Environment (TEE) while securely outsourcing the heavy linear layers of the model to the untrusted hardware accelerators.” Find the paper and full list of authors at the IEEE Symposium on Security and Privacy.
-
‘Secure Multiparty Computation With Identifiable Abort From Vindicating Release’
“In the dishonest-majority setting, generic secure multiparty computation (MPC) protocols are fundamentally vulnerable to attacks in which malicious participants learn their outputs and then force the protocol to abort before outputs are delivered to the honest participants. … We present a novel approach for realizing functionalities with a weak form of input-revealing [identifiable abort], which is based on delicate and selective revealing of committed input values. We refer to this new approach as vindicating release.” Find the paper and full list of authors at Cryptology ePrint Archive.
-
‘A Hybrid Partitioning Strategy for Backward Reachability of Neural Feedback Loops’
“As neural networks become more integrated into the systems that we depend on for transportation, medicine and security, it becomes increasingly important that we develop methods to analyze their behavior to ensure that they are safe to use within these contexts. The methods used in this paper seek to certify safety for closed-loop systems with neural network controllers, i.e., neural feedback loops, using backward reachability analysis.” Find the paper and full list of authors in the American Control Conference proceedings.
-
‘RAMP: A Risk-Aware Mapping and Planning Pipeline for Fast Off-Road Ground Robot Navigation’
“A key challenge in fast ground robot navigation in 3D terrain is balancing robot speed and safety. Recent work has shown that 2.5D maps (2D representations with additional 3D information) are ideal for real-time safe and fast planning. However, the prevalent approach of generating 2D occupancy grids through raytracing makes the generated map unsafe to plan in. … The RAMP pipeline proposed here solves these issues using new mapping and planning methods.” Find the paper and full list of authors at the IEEE International Conference on Robotics and Automation.
-
‘Level Assembly as a Markov Decision Process’
“Many games feature a progression of levels that doesn’t adapt to the player. This can be problematic because some players may get stuck … while others may find it boring if the progression is too slow to get to more challenging levels. This can be addressed by building levels based on the player’s performance and preferences. In this work, we formulate the problem of generating levels for a player as a Markov Decision Process (MDP) and use adaptive dynamic programming (ADP) to solve the MDP before assembling a level.” Find the paper and full list of authors at ArXiv.
-
‘Re-trainable Procedural Level Generation via Machine Learning (RT-PLGML) as Game Mechanic’
“We present re-trainable procedural level generation via machine learning (RT-PLGML), a game mechanic of providing in-game training examples for a PLGML system. We discuss opportunities and challenges, along with concept RT-PLGML games.” Find the paper and full list of authors at Proceedings of the 18th International Conference on the Foundations of Digital Games
-
‘Solder: Retrofitting Legacy Code with Cross-Language Patches’
“Internet-of-things devices are widely deployed, and suffer from easy-to-exploit security issues. … Because patch deployments tend to be focused on server-side vulnerabilities, client software in large codebases such as Apache may remain largely unpatched, and hence, vulnerable. … In this paper, we address this issue of leaving latent vulnerabilities in legacy codebases. We propose Solder, a framework to patch or retrofit legacy C/C++ code by replacing any target function with a newly-implemented one in a safe language such as Rust.” Find the paper and full list of authors in the International Conference on Software Analysis, Evolution and Reengineering proceedings.
-
‘On Regularity Lemma and Barriers in Streaming and Dynamic Matching’
“We present a new approach for finding matchings in dense graphs by building on Szemerédi’s celebrated Regularity Lemma. This allows us to obtain non-trivial albeit slight improvements over longstanding bounds for matchings in streaming and dynamic graphs.” Find the paper and full list of authors in the Proceedings of the 55th Annual ACM Symposium on Theory of Computing.
-
‘Complex Network Effects on the Robustness of Graph Convolutional Networks’
“Vertex classification — the problem of identifying the class labels of nodes in a graph — has applicability in a wide variety of domains. Examples include classifying subject areas of papers in citation networks or roles of machines in a computer network. Vertex classification using graph convolutional networks is susceptible to targeted poisoning attacks, in which both graph structure and node attributes can be changed in an attempt to misclassify a target node. … This paper considers an alternative: we leverage network characteristics in the training data selection process to improve robustness of vertex classifiers.” Find the paper and list…
-
Vincent Harris, research and industry leader in magnetic ceramics, receives lifetime achievement award
University Distinguished Professor Vincent Harris accepted a lifetime achievement award from the American Ceramic Society on Oct. 2 for his work on magnetoceramics, helping to usher in 5G technology.
-
‘PaniniQA: Enhancing Patient Education Through Interactive Question Answering’
“Patient portal allows discharged patients to access their personalized discharge instructions in electronic health records (EHRs). However, many patients have difficulty understanding or memorizing their discharge instructions. In this paper, we present PaniniQA, a patient-centric interactive question answering system designed to help patients understand their discharge instructions. PaniniQA first identifies important clinical content from patients’ discharge instructions and then formulates patient-specific educational questions.” Find the paper and full list of authors at ArXiv.
-
‘SEIL: Simulation-Augmented Equivariant Imitation Learning’
“In robotic manipulation … traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine learning tasks. However, image-level data augmentation is insufficient for an imitation learning agent to learn good manipulation policies in a reasonable amount of demonstrations. We propose Simulation-augmented Equivariant Imitation Learning (SEIL), a method that combines a novel data augmentation strategy of supplementing expert trajectories with simulated transitions and an equivariant model that exploits the O(2) symmetry in robotic manipulation.” Find the paper and full list of authors at the IEEE International Conference on Robotics and Automation proceedings.
-
‘Leveraging Symmetries in Pick and Place’
“A recently proposed [robotic] pick and place framework known as Transporter Net captures some of these symmetries, but not all. This paper analytically studies the symmetries present in planar robotic pick and place and proposes a method of incorporating equivariant neural models into Transporter Net in a way that captures all symmetries. The new model, which we call Equivariant Transporter Net, is equivariant to both pick and place symmetries and can immediately generalize pick and place knowledge to different pick and place poses.” Find the paper and full list of authors at ArXiv.
-
‘Balancing Biases and Preserving Privacy on Balanced Faces in the Wild’
“There are demographic biases present in current facial recognition (FR) models. To measure these biases across different ethnic and gender subgroups, we introduce our Balanced Faces in the Wild (BFW) dataset. … We found that relying on a single score threshold to differentiate between genuine and imposters sample pairs leads to suboptimal results. Additionally, performance within subgroups often varies significantly from the global average. … To mitigate imbalanced performances, we propose a novel domain adaptation learning scheme that uses facial features extracted from state-of-the-art neural networks.” Find the paper and full list of authors at IEEE Transactions on Image Processing.
-
‘Q: How To Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!’
“Finetuning a large vision language model (VLM) on a target dataset after large scale pretraining is a dominant paradigm in visual question answering (VQA). Datasets for specialized tasks such as knowledge-based VQA or VQA in non natural-image domains are orders of magnitude smaller than those for general-purpose VQA. While collecting additional labels for specialized tasks or domains can be challenging, unlabeled images are often available. We introduce SelTDA (Self-Taught Data Augmentation), a strategy for finetuning large VLMs on small-scale VQA datasets.” Find the paper and full list of authors at ArXiv.
-
‘SnapFusion: Text-to-Image Diffusion Model on Mobile Devices Within Two Seconds’
“Text-to-image diffusion models can create stunning images from natural language descriptions that rival the work of professional artists and photographers. However, these models are large, with complex network architectures and tens of denoising iterations, making them computationally expensive and slow to run. … This is costly and has privacy implications, especially when user data is sent to a third party. To overcome these challenges, we present a generic approach that, for the first time, unlocks running text-to-image diffusion models on mobile devices in less than 2 seconds.” Find the paper and full list of authors at ArXiv.
-
‘Hybrid Pixel-Unshuffled Network for Lightweight Image Super-resolution’
“Convolutional neural network (CNN) has achieved great success on image super-resolution (SR). However, most deep CNN-based SR models take massive computations to obtain high performance. Downsampling features for multi-resolution fusion is an efficient and effective way to improve the performance of visual recognition. Still, it is counter-intuitive in the SR task, which needs to project a low-resolution input to high-resolution. In this paper, we propose a novel Hybrid Pixel-Unshuffled Network (HPUN) by introducing an efficient and effective downsampling module into the SR task.” Find the paper and full list of authors in the AAAI Conference on Artificial Intelligence proceedings.
-
‘Generative Benchmark Creation for Table Union Search’
“Data management has traditionally relied on synthetic data generators to generate structured benchmarks … where we can control important parameters like data size and its distribution precisely. … Our current methods for creating benchmarks involve the manual curation and labeling of real data. These methods are not robust or scalable and … it is not clear how robust the created benchmarks are. We propose to use generative AI models to create structured data benchmarks for table union search. We present a novel method for using generative models to create tables with specified properties.” Find the paper and full list of…
-
‘Generative Multi-Label Correlation Learning’
“In real-world applications, … multi-label learning methods emerged in recent years. It is a more challenging problem for many reasons. … In general, overcoming these challenges and bettering learning performance could be achieved by utilizing more training samples and including label correlations. However, these solutions are expensive and inflexible. Large-scale, well-labeled datasets are difficult to obtain, and building label correlation maps requires task-specific semantic information as prior knowledge. To address these limitations, we propose a general and compact Multi-Label Correlation Learning (MUCO) framework.” Find the paper and full list of authors at ACM Transactions on Knowledge Discovery from Data.
-
‘Multitask Learning via Shared Features: Algorithms and Hardness’
“We investigate the computational efficiency of multitask learning of Boolean functions over the 𝑑-dimensional hypercube, that are related by means of a feature representation of size 𝑘≪𝑑 shared across all tasks. We present a polynomial time multitask learning algorithm for the concept class of halfspaces with margin 𝛾, which is based on a simultaneous boosting technique and requires only poly(𝑘/𝛾) samples-per-task and poly(𝑘log(𝑑)/𝛾) samples in total.” Find the paper and full list of authors in the Machine Learning Research proceedings.
-
‘SNAP: Efficient Extraction of Private Properties with Poisoning’
“Property inference attacks allow an adversary to extract global properties of the training dataset from a machine learning model. … Several existing approaches for property inference attacks against deep neural networks have been proposed, but they all rely on the attacker training a large number of shadow models. … We consider the setting of property inference attacks in which the attacker can poison a subset of the training dataset and query the trained target model.” Find the paper and full list of authors at the IEEE Symposium on Security and Privacy proceedings.
-
‘Smooth Lower Bounds for Differentially Private Algorithms via Padding-and-Permuting Fingerprinting Codes’
“Fingerprinting arguments … are the most widely used method for establishing lower bounds on the sample complexity or error of approximately differentially private (DP) algorithms. Still, there are many problems in differential privacy for which we don’t know suitable lower bounds, and even for problems that we do, the lower bounds are not smooth, and usually become vacuous when the error is larger than some threshold. In this work, we present a simple method to generate hard instances by applying a padding-and-permuting transformation to a fingerprinting code.” Find the paper and full list of authors at ArXiv.
-
‘Layout Representation Learning With Spatial and Structural Hierarchies’
“We present a novel hierarchical modeling method for layout representation learning, the core of design documents (e.g., user interface, poster, template). Existing works on layout representation often ignore element hierarchies, which is an important facet of layouts, and mainly rely on the spatial bounding boxes for feature extraction. This paper proposes a Spatial-Structural Hierarchical Auto-Encoder (SSH-AE) that learns hierarchical representation by treating a hierarchically annotated layout as a tree format.” Find the paper and full list of authors at the Proceedings of the AAAI Conference on Artificial Intelligence.
-
How does social media affect adolescent mental health? This researcher wants to find out
Assistant professor of psychology Alexandra Rodman is conducting a “digital phenotyping” study that will track how adolescents use their computers, cellphones and social media, and how this use impacts their risk for future mental health problems.
-
Ostadabbas selected as Eureka Award finalist within 2023 Oracle Excellence Awards
“Electrical and computer engineering associate professor Sarah Ostadabbas was selected as one of the finalists of the Eureka Award of the 2023 Oracle Excellence Awards. With Oracle for Research, researchers in academic, commercial and governmental settings, across all disciplines, are exploring novel ways to achieve ground-breaking results to make the world a better place.”
-
Designing exoskeletons to be more versatile and accessible
“Bouvé and mechanical and industrial engineering assistant professor Max Shepherd, in collaboration with Aaron Young from Georgia Tech, was awarded an $800,000 NSF grant for ‘Towards Task-Agnostic and Device-Agnostic Ankle Exoskeleton Control for Mobility Enhancement.'”
-
Improving power delivery for high-performance computing
“Electrical and computer engineerings professor Nian Sun and associate professor Aatmesh Shrivastava, in collaboration with Khurram Afridi and Huili (Grace) Xing from Cornell University, were awarded a $2,000,000 NSF grant for ‘Heterogeneous Integration in Power Electronics for High-Performance Computing (HIPE-HPC).’ This grant was awarded as part of the NSF Future of Semiconductors (FuSe) program.”