Title
Topic
-
‘Persistent Memory Research in the Post-Optane Era’
“After over a decade of researcher anticipation for the arrival of persistent memory (PMem), the first shipments of 3D XPoint-based Intel Optane Memory in 2019 were quickly followed by its cancellation in 2022. Was this another case of an idea quickly fading from future to past tense, relegating work in this area to the graveyard of failed technologies? … Without persistent memory itself, is future PMem research doomed? We offer two arguments for why reports of the death of PMem research are greatly exaggerated.” Find the paper and authors list in the Proceedings of the 1st Workshop on Disruptive Memory…
-
‘The Digital-Safety Risks of Financial Technologies for Survivors of Intimate Partner Violence’
“Digital technologies play a growing role in exacerbating financial abuse for survivors of intimate partner violence (IPV). … Scant research has examined how consumer-facing financial technologies can facilitate or obstruct IPV-related attacks on a survivor’s financial well-being. … We simulated both close-range and remote attacks commonly used by IPV adversaries. We discover that mobile banking and peer-to-peer payment applications are generally ill-equipped to deal with user-interface bound (UI-bound) adversaries, permitting unauthorized access to logins, surreptitious surveillance and harassing messages and system prompts.” Find the paper and full list of authors in the 32nd USENIX Security Symposium proceedings.
-
‘Continuing WebAssembly With Effect Handlers’
“WebAssembly (Wasm) is a low-level portable code format offering near native performance. It is intended as a compilation target for a wide variety of source languages. However, Wasm provides no direct support for non-local control flow features such as async/await, generators/iterators, lightweight threads, first-class continuations, etc. … We present WasmFX, an extension to Wasm which provides a universal target for non-local control features via effect handlers, enabling compilers to translate such features directly into Wasm. Our extension is minimal and only adds three main instructions for creating, suspending, and resuming continuations.” Find the paper and full list of authors at…
-
‘Discovering Informative and Robust Positives for Video Domain Adaptation’
Unsupervised domain adaptation for video recognition is challenging where the domain shift includes both spatial variations and temporal dynamics. Previous works have focused on exploring contrastive learning for cross-domain alignment. However, limited variations in intra-domain positives, false cross-domain positives, and false negatives hinder contrastive learning from fulfilling intra-domain discrimination and cross-domain closeness. This paper presents a non-contrastive learning framework without relying on negative samples for unsupervised video domain adaptation.” Find the paper and full list of authors at ICLR 2023.
-
‘Global Aligned Structured Sparsity Learning for Efficient Image Super-Resolution’
“Efficient image super-resolution (SR) has witnessed rapid progress thanks to novel lightweight architectures or model compression techniques (e.g., neural architecture search and knowledge distillation). Nevertheless, these methods consume considerable resources or/and neglect to squeeze out the network redundancy at a more fine-grained convolution filter level. … Structured pruning is known to be tricky when applied to SR networks because the extensive residual blocks demand the pruned indices of different layers to be the same. … In this article, we present Global Aligned Structured Sparsity Learning (GASSL) to resolve these problems.” Find the paper and full list of authors at IEEE…
-
‘HammerDodger: A Lightweight Defense Framework Against RowHammer Attack on DNNs’
“RowHammer attacks have become a serious security problem on deep neural networks (DNNs). Some carefully induced bit-flips degrade the prediction accuracy of DNN models to random guesses. This work proposes a lightweight defense framework that detects and mitigates adversarial bit-flip attacks. We employ a dynamic channel-shuffling obfuscation scheme to present moving targets to the attack, and develop a logits-based model integrity monitor with negligible performance loss.” Find the paper and full list of authors in the 2023 60th ACM/IEEE Design Automation Conference.
-
‘STABLE: Identifying and Mitigating Instability in Embeddings of the Degenerate Core’
“Are the embeddings of a graph’s degenerate core stable? What happens to the embeddings of nodes in the degenerate core as we systematically remove periphery nodes (by repeatedly peeling off κ-cores)? We discover three patterns w.r.t. instability in degenerate-core embeddings across a variety of popular graph embedding algorithms and datasets. We correlate instability with an increase in edge density, and then theoretically show that in the case of Erdös-Rényi graphs embedded with Laplacian Eigenmaps.” Find the paper and full list of authors in the Proceedings of the 2023 SIAM International Conference on Data Mining.
-
‘VertexSerum: Poisoning Graph Neural Networks for Link Inference’
“Graph neural networks (GNNs) have brought superb performance to various applications utilizing graph structural data, such as social analysis and fraud detection. The graph links, e.g., social relationships and transaction history, are sensitive and valuable information, which raises privacy concerns when using GNNs. To exploit these vulnerabilities, we propose VertexSerum, a novel graph poisoning attack that increases the effectiveness of graph link stealing by amplifying the link connectivity leakage. To infer node adjacency more accurately, we propose an attention mechanism that can be embedded into the link detection network.” Find the paper and full list of authors at ArXiv.
-
‘Implementation-Oblivious Transparent Checkpoint-Restart for MPI’
“This work presents experience with traditional use cases of checkpointing on a novel platform. A single codebase (MANA) transparently checkpoints production workloads for major available MPI implementations: “develop once, run everywhere”. The new platform enables application developers to compile their application against any of the available standards-compliant MPI implementations, and test each MPI implementation according to performance or other features.” Find the paper and full list of authors at ArXiv.
-
‘Ecosystem-Level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes’
“Machine learning is traditionally studied at the model level: researchers measure and improve the accuracy, robustness, bias, efficiency, and other dimensions of specific models. In practice, the societal impact of machine learning is determined by the surrounding context of machine learning deployments. To capture this, we introduce ecosystem-level analysis: rather than analyzing a single model, we consider the collection of models that are deployed in a given context.” Find the paper and full list of authors at ArXiv.
-
‘Random Oracle Combiners: Breaking the Concatenation Barrier for Collision-Resistance’
“Suppose two parties have hash functions h1 and h2 respectively, but each only trusts the security of their own. We wish to build a hash combiner Cʰ¹,ʰ² which is secure so long as either one of the underlying hash functions is. … In this case, concatenating the two hash outputs clearly works. Unfortunately, a long series of works … showed no (noticeably) shorter combiner for collision resistance is possible. … We argue the right formulation of the “hash combiner” is what we call random oracle (RO) combiners.” Find the paper and full list of authors at Cryptology ePrint Archive.
-
‘Security With Functional Re-Encryption From CPA
“The notion of functional re-encryption security (funcCPA) for public-key encryption schemes was recently introduced by Akavia et al. (TCC’22), in the context of homomorphic encryption. This notion lies in between CPA security and CCA security: we give the attacker a functional re-encryption oracle instead of the decryption oracle of CCA security. … In this work we observe that funcCPA security may have applications beyond homomorphic encryption and set out to study its properties.” Find the paper and full list of authors at Cryptology ePrint Archive.
-
‘BIT: Bi-Level Temporal Modeling for Efficient Supervised Action Segmentation’
“We address the task of supervised action segmentation which aims to partition a video into non-overlapping segments, each representing a different action. Recent works apply transformers to perform temporal modeling at the frame-level, which suffer from high computational cost and cannot well capture action dependencies over long temporal horizons. To address these issues, we propose an efficient BI-level Temporal modeling (BIT) framework that learns explicit action tokens to represent action segments, in parallel performs temporal modeling on frame and action levels, while maintaining a low computational cost.” Find the paper and full list of authors at ArXiv.
-
‘Real-Time Neural Light Field on Mobile Devices’
“Recent efforts in Neural Rendering Fields (NeRF) have shown impressive results on novel view synthesis by utilizing implicit neural representation to represent 3D scenes. Due to the process of volumetric rendering, the inference speed for NeRF is extremely slow. … Another emerging direction utilizes the neural light field (NeLF) for speedup, as only one forward pass is performed on a ray to predict the pixel color. … In this work, we propose an efficient network that runs in real-time on mobile devices for neural rendering.” Find the paper and full list of authors at ArXiv.
-
‘Latent Graph Inference With Limited Supervision’
“Latent graph inference (LGI) aims to jointly learn the underlying graph structure and node representations from data features. However, existing LGI methods commonly suffer from the issue of supervision starvation, where massive edge weights are learned without semantic supervision. … In this paper, we observe that this issue is actually caused by the graph sparsification operation, which severely destroys the important connections established between pivotal nodes and labeled ones. To address this, we propose to restore the corrupted affinities and replenish the missed supervision for better LGI.” Find the paper and authors list at ArXiv.
-
‘A Tutorial on Visual Representations of Relational Queries’
“Query formulation is increasingly performed by systems that need to guess a user’s intent. … But how can a user know that the computational agent is returning answers to the “right” query? More generally, given that relational queries can become pretty complicated, how can we help users understand existing relational queries, whether human-generated or automatically generated? Now seems the right moment to revisit a topic that predates the birth of the relational model: developing visual metaphors that help users understand relational queries. This lecture-style tutorial surveys the key visual metaphors developed for visual representations of relational expressions.”
-
‘Pixel-Aligned Recurrent Queries for Multi-View 3D Object Detection’
“We present PARQ – a multi-view 3D object detector with transformer and pixel-aligned recurrent queries. Unlike previous works that use learnable features or only encode 3D point positions as queries in the decoder, PARQ leverages appearance-enhanced queries initialized from reference points in 3D space and updates their 3D location with recurrent cross-attention operations. Incorporating pixel-aligned features and cross attention enables the model to encode the necessary 3D-to-2D correspondences and capture global contextual information of the input images.” Find the paper and full list of authors at ArXiv.
-
‘SportsSloMo: A New Benchmark and Baselines for Human-centric Video Frame Interpolation’
“Human-centric video frame interpolation has great potential for improving people’s entertainment experiences and finding commercial applications in the sports analysis industry. … Although there are multiple benchmark datasets available in the community, none of them is dedicated for human-centric scenarios. To bridge this gap, we introduce SportsSloMo, a benchmark consisting of more than 130K video clips and 1M video frames of high-resolution (≥720p) slow-motion sports videos crawled from YouTube. We re-train several state-of-the-art methods on our benchmark, and the results show a decrease in their accuracy compared to other datasets.” Find the paper and full list of authors at ArXiv.
-
‘Social Functions of Machine Emotional Expressions’
“Virtual humans and social robots frequently generate behaviors that human observers naturally see as expressing emotion. In this review article, we highlight that these expressions can have important benefits for human–machine interaction. We first summarize the psychological findings on how emotional expressions achieve important social functions in human relationships and highlight that artificial emotional expressions can serve analogous functions in human–machine interaction. We then review computational methods for determining what expressions make sense to generate within the context of interaction and how to realize those expressions across multiple modalities.” Find the paper and full list of authors in IEEE Proceedings.
-
‘Large Language Models in Textual Analysis for Gesture Selection’
“Gestures perform a variety of communicative functions that powerfully influence human face-to-face interaction. … Approaches to automatic gesture generation vary not only in the degree to which they rely on data-driven techniques but also the degree to which they can produce context and speaker specific gestures. However, these approaches face two major challenges. … Here, we approach these challenges by using large language models (LLMs) to show that these powerful models of large amounts of data can be adapted for gesture analysis and generation.” Find the paper and full list of authors in the 25th International Conference on Multimodal Interaction…
-
‘Blend: A Unified Data Discovery System’
“Data discovery is an iterative and incremental process that necessitates the execution of multiple data discovery queries to identify the desired tables from large and diverse data lakes. Current methodologies concentrate on single discovery tasks such as join, correlation, or union discovery. However, in practice, a series of these approaches and their corresponding index structures are necessary. … This paper presents BLEND, a comprehensive data discovery system that empowers users to develop ad-hoc discovery tasks without the need to develop new algorithms or build a new index structure.” Find the paper and full list of authors at ArXiv.
-
‘Detecting Receptivity for mHealth Interventions’
“Just-In-Time Adaptive Interventions (JITAI) have the potential to provide effective support for health behavior by delivering the right type and amount of intervention at the right time. … Previous research has explored the association of context and user-specific traits on receptivity and built machine-learning models to detect receptivity after the study was completed. However, for effective intervention delivery, JITAI systems need to make in-the-moment decisions about a user’s receptivity. In this study, we deployed machinelearning models in a chatbot-based digital coach to predict receptivity for physical-activity interventions.” Find the paper and full list of authors in SIGMOBILE.
-
‘Modeling Self-Propagating Malware With Epidemiological Models’
“Self-propagating malware (SPM) is responsible for large financial losses and major data breaches with devastating social impacts that cannot be understated. Well-known campaigns such as WannaCry and Colonial Pipeline have been able to propagate rapidly on the Internet and cause widespread service disruptions. To date, the propagation behavior of SPM is still not well understood. … Here, we address this gap by performing a comprehensive analysis of a newly proposed epidemiological-inspired model for SPM propagation, the Susceptible-Infected-Infected Dormant-Recovered (SIIDR) model.” Find the paper and full list of authors at Applied Network Science.
-
‘Latent Space Symmetry Discovery’
“Equivariant neural networks require explicit knowledge of the symmetry group. Automatic symmetry discovery methods aim to relax this constraint and learn invariance and equivariance from data. However, existing symmetry discovery methods are limited to linear symmetries in their search space and cannot handle the complexity of symmetries in real-world, often high-dimensional data. We propose a novel generative model, Latent LieGAN (LaLiGAN), which can discover nonlinear symmetries from data. It learns a mapping from data to a latent space where the symmetries become linear and simultaneously discovers symmetries in the latent space.” Find the paper and list of authors at ArXiv.
-
‘ICML 2023 Topological Deep Learning Challenge : Design and Results’
“This paper presents the computational challenge on topological deep learning that was hosted within the ICML 2023 Workshop on Topology and Geometry in Machine Learning. The competition asked participants to provide open-source implementations of topological neural networks from the literature by contributing to the python packages TopoNetX (data processing) and TopoModelX (deep learning). The challenge attracted twenty-eight qualifying submissions in its two-month duration. This paper describes the design of the challenge and summarizes its main findings.” Find the paper and full list of authors at ArXiv.
-
‘Chameleon: Increasing Label-Only Membership Leakage With Adaptive Poisoning’
“The integration of machine learning (ML) in numerous critical applications introduces a range of privacy concerns for individuals who provide their datasets for model training. One such privacy risk is Membership Inference (MI), in which an attacker seeks to determine whether a particular data sample was included in the training dataset. … MI attacks capitalize on access to the model’s predicted confidence scores to successfully perform membership inference, and employ data poisoning to further enhance their effectiveness. … We show that existing label-only MI attacks are ineffective at inferring membership.” Find the paper and full list of authors at ArXiv.
-
Panel discussion for CSCW ’23: ‘Getting Data for CSCW Research’
“This panel will bring together a group of scholars from diverse methodological backgrounds to discuss critical aspects of data collection for CSCW research. This discussion will consider the rapidly evolving ethical, practical, and data access challenges, examine the solutions our community is currently deploying and envision how to ensure vibrant CSCW research going forward.” Find the full list of panelists in the Companion Publication of the 2023 Conference on Computer Supported Cooperative Work and Social Computing.
-
‘Lower Bounds on Anonymous Whistleblowing’
“Anonymous transfer … allows a sender to leak a message anonymously by participating in a public non-anonymous discussion where everyone knows who said what. … The work of [ACM22] presented a lower bound on anonymous transfer, ruling out constructions with strong anonymity guarantees. … They also provided a (heuristic) upper bound, giving a scheme with weak anonymity guarantees. … In this work, we present improved lower bounds on anonymous transfer, that rule out both of the above possibilities.” Find the paper and full list of authors at the Cryptology ePrint Archive.
-
‘Relaxed Octahedral Group Convolution for Learning Symmetry Breaking in 3D Physical Systems’
“Deep equivariant models use symmetries to improve sample efficiency and generalization. However, the assumption of perfect symmetry in many of these models can sometimes be restrictive, especially when the data does not perfectly align with such symmetries. Thus, we introduce relaxed octahedral group convolution for modeling 3D physical systems in this paper. This flexible convolution technique provably allows the model to both maintain the highest level of equivariance that is consistent with data and discover the subtle symmetry-breaking factors in the physical systems.” Find the paper and full list of authors at ArXiv.