Publications
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Sort By
1 - 15 of 10129 publications
On the Robustness of Image-based Malware Detection against Adversarial Attacks
Yassine Mekdad
Harun Oz
Ahmet Aris
Leonardo Babun
Faraz Naseem
Selcuk Uluagac
Nasir Ghani
Abbas Acar
Network Security Empowered by Artificial Intelligence, Springer (2024)
Preview abstract
Machine and deep learning models are now one of the most valuable tools in the arsenal of computer security practitioners. Their success has been demonstrated in various network-security-oriented applications such as intrusion detection, cyber threat intelligence, vulnerability discovery, and malware detection. Nevertheless, recent research studies have shown that crafted adversarial samples can be used to evade malware detection models. Even though several defense mechanisms such as adversarial training have been proposed in the malware detection domain to address this issue, they unfortunately suffer from model poisoning and low detection accuracy. In this chapter, we assess the robustness of image-based malware classifier against four different adversarial attacks: (a) random and benign brute-force byte append attacks for black-box settings and (b) random and benign Fast Gradient Sign Method (FGSM) attacks for white-box settings. To this end, we implement a Convolutional Neural Network (CNN) to classify the image representations of Windows Portable Executable (PE) malware with a detection accuracy of 95.05%. Then, we evaluate its robustness along with MalConv, a state-of-the-art malware classifier, by applying a set of functionality-preserving adversarial attacks. Our experimental results demonstrate that image-based classifier exhibits a lower evasion rate of 5% compared to MalConv that achieves an evasion rate ranging between 44 and 54% in black-box settings. However, in white-box settings, both models fail against random byte and benign byte FGSM attacks, with an evasion rate of more than 46%.
View details
A data-centric perspective on the information needed for hydrological uncertainty predictions
Andreas Auer
Martin Gauch
Frederik Kratzert
Sepp Hochreiter
Daniel Klotz
Hydrology and Earth System Sciences (2024)
Preview abstract
Uncertainty estimates are fundamental to assess the reliability of predictive models in hydrology. We use the framework of conformal prediction to investigate the impact of temporal and spatial information on uncertainty estimates within hydrological predictions. Integrating recent information significantly enhances overall uncertainty predictions, even with substantial gaps between updates. While local information yields good results on average, it proves to be insufficient for peak-flow predictions. Incorporating global information improves the accuracy of peak-flow bounds, corroborating findings from related studies. Overall, the study underscores the importance of continuous data updates and the integration of global information for robust and efficient uncertainty estimation.
View details
Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding
Alizée Pace
Hugo Yèche
Bernhard Schölkopf
Gunnar Rätsch
The Twelfth International Conference on Learning Representations (2024)
Preview abstract
A prominent challenge of offline reinforcement learning (RL) is the issue of hidden confounding. There, unobserved variables may influence both the actions taken by the agent and the outcomes observed in the data. Hidden confounding can compromise the validity of any causal conclusion drawn from the data and presents a major obstacle to effective offline RL. In this paper, we tackle the problem of hidden confounding in the nonidentifiable setting. We propose a definition of uncertainty due to confounding bias, termed delphic uncertainty, which uses variation over compatible world models, and differentiate it from the well known epistemic and aleatoric uncertainties. We derive a practical method for estimating the three types of uncertainties, and construct a pessimistic offline RL algorithm to account for them. Our method does not assume identifiability of the unobserved confounders, and attempts to reduce the amount of confounding bias. We demonstrate through extensive experiments and ablations the efficacy of our approach on a sepsis management benchmark, as well as real electronic health records. Our results suggest that nonidentifiable confounding bias can be addressed in practice to improve offline RL solutions.
View details
Using large language models to accelerate communication for eye gaze typing users with ALS
Subhashini Venugopalan
Katie Seaver
Xiang Xiao
Sri Jalasutram
Ajit Narayanan
Bob MacDonald
Emily Kornman
Daniel Vance
Blair Casey
Steve Gleason
(2024)
Preview abstract
Accelerating text input in augmentative and alternative communication (AAC) is a long-standing area of research with bearings on the quality of life in individuals with profound motor impairments. Recent advances in large language models (LLMs) pose opportunities for re-thinking strategies for enhanced text entry in AAC. In this paper, we present SpeakFaster, consisting of an LLM-powered user interface for text entry in a highly-abbreviated form, saving 57% more motor actions than traditional predictive keyboards in offline simulation. A pilot study on a mobile device with 19 non-AAC participants demonstrated motor savings in line with simulation and relatively small changes in typing speed. Lab and field testing on two eye-gaze AAC users with amyotrophic lateral sclerosis demonstrated text-entry rates 29–60% above baselines, due to significant saving of expensive keystrokes based on LLM predictions. These findings form a foundation for further exploration of LLM-assisted text entry in AAC and other user interfaces.
View details
A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models
Heather Cole-Lewis
Nenad Tomašev
Liam McCoy
Leo Anthony Celi
Alanna Walton
Akeiylah DeWitt
Philip Mansfield
Sushant Prakash
Joelle Barral
Ivor Horn
Karan Singhal
Nature Medicine (2024)
Preview abstract
Large language models (LLMs) hold promise to serve complex health information needs but also have the potential to introduce harm and exacerbate health disparities. Reliably evaluating equity-related model failures is a critical step toward developing systems that promote health equity. We present resources and methodologies for surfacing biases with potential to precipitate equity-related harms in long-form, LLM-generated answers to medical questions and conduct a large-scale empirical case study with the Med-PaLM 2 LLM. Our contributions include a multifactorial framework for human assessment of LLM-generated answers for biases and EquityMedQA, a collection of seven datasets enriched for adversarial queries. Both our human assessment framework and our dataset design process are grounded in an iterative participatory approach and review of Med-PaLM 2 answers. Through our empirical study, we find that our approach surfaces biases that may be missed by narrower evaluation approaches. Our experience underscores the importance of using diverse assessment methodologies and involving raters of varying backgrounds and expertise. While our approach is not sufficient to holistically assess whether the deployment of an artificial intelligence (AI) system promotes equitable health outcomes, we hope that it can be leveraged and built upon toward a shared goal of LLMs that promote accessible and equitable healthcare.
View details
A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains
Alon Jacovi
Or Honovich
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (2024), pp. 4615–4634
Preview abstract
Prompting language models to provide step-by-step answers (e.g., “Chain-of-Thought”) is the prominent approach for complex reasoning tasks, where more accurate reasoning chains typically improve downstream task performance. Recent literature discusses automatic methods to verify reasoning to evaluate and improve their correctness. However, no fine-grained step-level datasets are available to enable thorough evaluation of such verification methods, hindering progress in this direction. We introduce REVEAL: Reasoning Verification Evaluation, a dataset to benchmark automatic verifiers of complex Chain-of-Thought reasoning in open-domain question-answering settings. REVEAL includes comprehensive labels for the relevance, attribution to evidence passages, and logical correctness of each reasoning step in a language model’s answer, across a variety of datasets and state-of-the-art language models. Evaluation on REVEAL shows that verifiers struggle at verifying reasoning chains — in particular, verifying logical correctness and detecting contradictions. Available at https://reveal-dataset.github.io/.
View details
Creativity, Generative AI, and Software Development: A Research Agenda
Victoria Jackson
Bogdan Vasilescu
Daniel Russo
Paul Ralph
Maliheh Izadi
Rafael Prikladnicki
Anielle Lisboa
Andre van der Hoek
Preview abstract
Creativity has always been considered a major differentiator to separate the good from the great, and we believe the importance of creativity to software development will only increase as GenAI becomes embedded in developer tool-chains and working practices. This paper uses the McLuhan tetrad alongside scenarios of how GenAI may disrupt software development more broadly, to identify potential impacts GenAI may have on creativity within software development. The impacts are discussed along with a future research agenda comprising of six connected themes that consider how individual capabilities, team capabilities, the product, unintended consequences, society, and human aspects can be affected.
View details
See Through Vehicles: Fully Occluded Vehicle Detection with Millimeter Wave Radar
Chenming He
Chengzhen Meng
Chunwang He
Beibei Wang
Yubo Yan
Yanyong Zhang
MobiCom 2024: The 30th Annual International Conference On Mobile Computing And Networking
Preview abstract
A crucial task in autonomous driving is to continuously detect nearby vehicles. Problems thus arise when a vehicle is occluded and becomes “unseeable”, which may lead to accidents. In this study, we develop mmOVD, a system that can detect fully occluded vehicles by involving millimeter-wave radars to capture the ground-reflected signals passing beneath the blocking vehicle’s chassis. The foremost challenge here is coping with ghost points caused by frequent multi-path reflections, which highly resemble the true points. We devise a set of features that can efficiently distinguish the ghost points by exploiting the neighbor points’ spatial and velocity distributions. We also design a cumulative clustering algorithm to effectively aggregate the unstable ground reflected radar points over consecutive frames to derive the bounding boxes of the vehicles.
We have evaluated mmOVD in both controlled environments and real-world environments. In an underground garage and two campus roads, we conducted controlled experiments in 56 scenes with 8 vehicles, including a minibus and a motorcycle. Our system accurately detects occluded vehicles for the first time, with a 91.1% F1 score for occluded vehicle detection and a 100% success rate for occlusion event detection. More importantly, we drove 324km on crowded roads at a speed up to 70km per hour and show we could achieve an occlusion detection success rate of 92% and a low false alarm rate of 4% with only 10% of the training data in complex real-world environments.
View details
Efficiency of the Generalized Second-Price Auction for Value Maximizers
Hanrui Zhang
Proceedings of the ACM on Web Conference 2024, 46–56
Preview abstract
We study the price of anarchy of the generalized second-price auction where bidders are value maximizers (i.e., autobidders). We show that in general the price of anarchy can be as bad as 0. For comparison, the price of anarchy of running VCG is 1/2 in the autobidding world. We further show a fined-grained price of anarchy with respect to the discount factors (i.e., the ratios of click probabilities between lower slots and the highest slot in each auction) in the generalized second-price auction, which highlights the qualitative relation between the smoothness of the discount factors and the efficiency of the generalized second-price auction.
View details
Preview abstract
There is a potential future where the content created by a human and an AI are indistinguishable. In this future, if you can’t tell the difference, does it matter? We conducted a 3 (Assigned creator: human, human with AI assistance, AI) by 4 (Context: news, travel, health, and jokes) mixed-design experiment where participants evaluated human-written content that was presented as created by a human, a human with AI assistance, or an AI. We found that participants felt more negatively about the content creator and were less satisfied when they thought AI was used, but assigned creator had no effect on content judgments. We also identified five interpretations for how participants thought AI use affected the content creation process. Our work suggests that informing users about AI use may not have the intended effect of helping consumers make content judgments and may instead damage the relationship
between creators and followers.
View details
Perspective Chapter: Assessment of Subjective and Objective Sleep Quality from Wrist-Worn Wearable Data
Ben Yetton
Daniel McDuff
Andrew Barakat
Allen Jiang
Nicholas Allen
Logan Schneider
Ari Winbush
Conor Heneghan
Preview abstract
Researchers are interested in measuring both objective and subjective assessments of sleep, and associated phenomena such as sleepiness, quality and restoration. Predicting perceived sleep quality accurately from objective measurements remains an unsolved and interesting problem. Previous studies using polysomnograms and actigraphy have shown poor concordance between objective metrics and subjective sleep quality, but were often limited by study duration (e.g., one or two nights of PSG, study population in low 100 s). In this chapter, we consider whether consumer sleep trackers could significantly improve the assessment of subjective sleep quality through longer periods of assessment and larger data scale. We describe a recent study that modeled two subjective sleep quality metrics (PROMIS Sleep-Related Impairment (SI) and Sleep Disturbance (SD) Index) from objective sleep metrics acquired from a consumer wearable device (Fitbit). However, the goodness-of-fit parameter remains relatively low, even with the increased data availability and scale of data provided by consumer wearables. Specifically, for a well-characterized normative population of 2106 adults, we see that a linear multivariate model produces an R2 of 0.107 for predicting SI and R2 of 0.147 for SR, consistent with prior results using PSG and actigraphy. We conclude that subjective sleep quality remains broadly a psychological construct that cannot be fully modeled solely by objective sleep metrics.
View details
WSDM 2024 Workshop on Large Language Models for Individuals, Groups, and Society
Qiaozhu Mei
Vanessa Murdock
Jie Tang
Hongning Wang
Hamed Zamani
(2024) (to appear)
Preview abstract
This workshop discusses the cutting-edge developments in research and applications of personalizing large language models (LLMs) and adapting them to the demands of diverse user populations and societal needs. The full-day workshop plan includes several keynotes and invited talks, a poster session and a panel discussion.
View details
Dynamic Inference of Likely Symbolic Tensor Shapes in Python Machine Learning Programs
Koushik Sen
International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) (2024) (to appear)
Preview abstract
In machine learning programs, it is often tedious to annotate the dimensions of shapes of various tensors that get created during execution. We present a dynamic likely tensor shape inference analysis that annotates the dimensions of shapes of tensor expressions with symbolic dimension values. Such annotations can be used for understanding the machine learning code written in popular frameworks, such as TensorFlow, PyTorch, JAX, and for finding bugs related to tensor shape mismatch.
View details
Preview abstract
Current approaches to Analog Layout Automation
apply ML techniques such as Graph Convolutional Neural
Networks (GCN) to translate netlist to layout. While these ML
approaches have proven to be effective, they lack the powerful
reasoning capabilities, an intuitive human interface, and standard
evaluation benchmarks that have been improving at a rapid de-
velopment pace in Large Language Models (LLMs). The GLayout
framework introduced in this work translates analog layout into
an expressive, technology generic, compact text representation.
Then, an LLM is taught to understand analog layout through
fine-tuning and in-context learning using Retrieval Augmented
Generation (RAG). The LLM is able to successfully layout unseen
circuits based on new information provided in-context. We train
3.8, 7, and 22 Billion parameter quantized LLMs on a dataset
of less than 50 unique circuits, and text documents providing
layout knowledge. The 22B parameter model is tuned in 2 hours
on a single NVIDIA A100 GPU. The open-source evaluation
set is proposed as an automation benchmark for LLM layout
automation tasks, and ranges from 2-transistor circuits to a
∆Σ ADC. The 22B model completes 70% of the tasks in the
evaluation set, and is able to pass DRC and LVS verification on
unseen 4 transistor blocks.
View details
Meta-Manager: A Tool for Collecting and Exploring Meta Information about Code
Amber Horvath
Brad A. Myers
CHI '24: Proceedings of the CHI Conference on Human Factors in Computing Systems (2024)
Preview abstract
Modern software engineering is in a state of flux. With more development utilizing AI code generation tools and the continued reliance on online programming resources, understanding code and the original intent behind it is becoming more important than it ever has been. To this end, we have developed the “Meta-Manager”, a Visual Studio Code extension, with a supplementary browser extension, that automatically collects and organizes changes made to code while keeping track of the provenance of each part of the code, including code that has been copy-pasted from popular programming resources online. These sources and subsequent changes are represented in the editor and may be explored using searching and filtering mechanisms to help developers answer historically hard-to-answer questions about code, its provenance, and its design rationale. In our evaluation of Meta-Manager, we found developers
were successfully able to use it to answer otherwise unanswerable questions about an unfamiliar code base.
View details
