Search Results for author:
Found 49 papers, 27 papers with code
Beyond the Single Neuron Convex Barrier for Neural Network Certification
We propose a new parametric framework, called k-ReLU, for computing precise and scalable convex relaxations used to certify neural networks.
A Provable Defense for Deep Residual Networks
We present a training system, which can provably defend significantly larger neural networks than previously possible, including ResNet-34 and DenseNet-100.
Improving LLM Code Generation with Grammar Augmentation
We present SynCode a novel framework for efficient and general syntactical decoding of code with large language models (LLMs).
Learning Topological Interactions for Multi-Class Medical Image Segmentation
In this paper, we introduce a novel topological interaction module to encode the topological interactions into a deep neural network.
BLEND: A Fast, Memory-Efficient, and Accurate Mechanism to Find Fuzzy Seed Matches in Genome Analysis
We introduce BLEND, the first efficient and accurate mechanism that can identify both exact-matching and highly similar seeds with a single lookup of their hash values, called fuzzy seed matches.
RawHash: Enabling Fast and Accurate Real-Time Analysis of Raw Nanopore Signals for Large Genomes
RawHash achieves an accurate hash-based similarity search via an effective quantization of the raw signals such that signals corresponding to the same DNA content have the same quantized value and, subsequently, the same hash value.
Sibyl: Adaptive and Extensible Data Placement in Hybrid Storage Systems Using Online Reinforcement Learning
We introduce Sibyl, the first technique that uses reinforcement learning for data placement in hybrid storage systems.
Adversarial Attacks on Probabilistic Autoregressive Forecasting Models
We develop an effective generation of adversarial attacks on neural models that output a sequence of probability distributions rather than a sequence of single values.
Certifying Geometric Robustness of Neural Networks
The use of neural networks in safety-critical computer vision systems calls for their robustness certification against natural geometric transformations (e. g., rotation, scaling).
An Experimental Evaluation of Machine Learning Training on a Real Processing-in-Memory System
Our K-Means clustering on PIM is $2. 8\times$ and $3. 2\times$ than state-of-the-art CPU and GPU versions, respectively.
Bypassing the Safety Training of Open-Source LLMs with Priming Attacks
With the recent surge in popularity of LLMs has come an ever-increasing need for LLM safety training.
Shared Certificates for Neural Network Verification
We perform an extensive experimental evaluation to demonstrate the effectiveness of shared certificates in reducing the verification cost on a range of datasets and attack specifications on image classifiers including the popular patch and geometric perturbations.
FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices using a Computing Power Aware Scheduler
Nonetheless, because of the disparity of computing resources among different clients (i. e., device heterogeneity), synchronous federated learning algorithms suffer from degraded efficiency when waiting for straggler clients.
Robustness Certification for Point Cloud Models
In this work, we address this challenge and introduce 3DCertify, the first verifier able to certify the robustness of point cloud models.
Going From Molecules to Genomic Variations to Scientific Discovery: Intelligent Algorithms and Architectures for Intelligent Genome Analysis
We hope that these efforts and the challenges we discuss provide a foundation for future work in making genome analysis more intelligent.
Scalable Polyhedral Verification of Recurrent Neural Networks
We present a scalable and precise verifier for recurrent neural networks, called Prover based on two novel ideas: (i) a method to compute a set of polyhedral abstractions for the non-convex and nonlinear recurrent update functions by combining sampling, optimization, and Fermat's theorem, and (ii) a gradient descent based algorithm for abstraction refinement guided by the certification problem that combines multiple abstractions for each neuron.
Incremental Verification of Neural Networks
Complete verification of deep neural networks (DNNs) can exactly determine whether the DNN satisfies a desired trustworthy property (e. g., robustness, fairness) on an infinite set of inputs or not.
Lung Swapping Autoencoder: Learning a Disentangled Structure-texture Representation of Chest Radiographs
Well-labeled datasets of chest radiographs (CXRs) are difficult to acquire due to the high cost of annotation.
TargetCall: Eliminating the Wasted Computation in Basecalling via Pre-Basecalling Filtering
However, for many applications, the majority of reads do no match the reference genome of interest (i. e., target reference) and thus are discarded in later steps in the genomics pipeline, wasting the basecalling computation.
Incremental Randomized Smoothing Certification
We experimentally demonstrate the effectiveness of our approach, showing up to 3x certification speedup over the certification that applies randomized smoothing of the approximate model from scratch.
Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning
We study reward poisoning attacks on online deep reinforcement learning (DRL), where the attacker is oblivious to the learning algorithm used by the agent and the dynamics of the environment.
Is Watermarking LLM-Generated Code Robust?
We present the first study of the robustness of existing watermarking techniques on Python code generated by large language models.
Probabilistic Trust Intervals for Out of Distribution Detection
In this paper, we propose a very simple approach for enhancing the ability of a pretrained network to detect OOD inputs without even altering the original parameter values.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Scalable Verification of GNN-based Job Schedulers
Recently, Graph Neural Networks (GNNs) have been applied for scheduling jobs over clusters, achieving better performance than hand-crafted heuristics.
COMET: Neural Cost Model Explanation Framework
We generate and compare COMET's explanations for the popular neural cost model, Ithemal against those for an accurate CPU simulation-based cost model, uiCA.
Fast and Effective Robustness Certification
We present a new method and system, called DeepZ, for certifying neural network robustness based on abstract interpretation.
Robustness Certification with Refinement
We present a novel approach for verification of neural networks which combines scalable over-approximation methods with precise (mixed integer) linear programming.
Agile Autotuning of a Transprecision Tensor Accelerator Overlay for TVM Compiler Stack
Specialized accelerators for tensor-operations, such as blocked-matrix operations and multi-dimensional convolutions, have been emerged as powerful architecture choices for high-performance Deep-Learning computing.
Can tumor location on pre-treatment MRI predict likelihood of pseudo-progression versus tumor recurrence in Glioblastoma? A feasibility study
In this study, 74 pre-treatment Glioblastoma MRI scans with PsP (33) and tumor recurrence (41) were analyzed.
Predicting Clinical Outcomes in COVID-19 using Radiomics and Deep Learning on Chest Radiographs: A Multi-Institutional Study
Radiomic and DL classification models had mAUCs of 0. 78+/-0. 02 and 0. 81+/-0. 04, compared with expert scores mAUCs of 0. 75+/-0. 02 and 0. 79+/-0. 05 for mechanical ventilation requirement and mortality prediction, respectively.
Scaling Polyhedral Neural Network Verification on GPUs
GPUPoly scales to large networks: for example, it can prove the robustness of a 1M neuron, 34-layer deep residual network in approximately 34. 5 ms. We believe GPUPoly is a promising step towards practical verification of real-world neural networks.
Provably Robust Adversarial Examples
We introduce the concept of provably robust adversarial examples for deep neural networks - connected input regions constructed from standard adversarial examples which are guaranteed to be robust to a set of real-world perturbations (such as changes in pixel intensity and geometric transformations).
PRIMA: General and Precise Neural Network Certification via Scalable Convex Hull Approximations
Formal verification of neural networks is critical for their safe adoption in real-world applications.
Radiomic Deformation and Textural Heterogeneity (R-DepTH) Descriptor to characterize Tumor Field Effect: Application to Survival Prediction in Glioblastoma
Our work is based on the rationale that highly aggressive tumors tend to grow uncontrollably, leading to pronounced biomechanical tissue deformations in the normal parenchyma, which when combined with local morphological differences in the tumor confines on MRI scans, will comprehensively capture tumor field effect.
Attention based CNN-LSTM Network for Pulmonary Embolism Prediction on Chest Computed Tomography Pulmonary Angiograms
In this study we propose a two-stage attention-based CNN-LSTM network for predicting PE, its associated type (chronic, acute) and corresponding location (leftsided, rightsided or central) on computed tomography (CT) examinations.
Attention-based Multi-scale Gated Recurrent Encoder with Novel Correlation Loss for COVID-19 Progression Prediction
This vector is used as an input to a decoder module to predict patch severity grades at a future timepoint.
Practical Adversarial Attacks on Brain--Computer Interfaces
We propose new methods to induce denial-of-service attacks and incorporate domain-specific insights and constraints to accomplish two key goals: (i) create smooth adversarial attacks that are physiologically plausible; (ii) consider the realistic case where the attack happens at the origin of the signal acquisition and it propagates on the human head.
Language Modelling via Learning to Rank
We also develop a method using $N$-grams to create a non-probabilistic teacher which generates the ranks without the need of a pre-trained LM.
Certifying Neural Network Audio Classifiers
We present the first end-to-end verifier of audio classifiers.
Machine Learning Training on a Real Processing-in-Memory System
Our goal is to understand the potential of modern general-purpose PIM architectures to accelerate machine learning training.
Robust Universal Adversarial Perturbations
We further show that by using a set of primitive transformations our method can generalize well to unseen transformations such as fog, JPEG compression, etc.
Provable Defense Against Geometric Transformations
Geometric image transformations that arise in the real world, such as scaling and rotation, have been shown to easily deceive deep neural networks (DNNs).
LEAPER: Fast and Accurate FPGA-based System Performance Prediction via Transfer Learning
The key idea of LEAPER is to transfer an ML-based performance and resource usage model trained for a low-end edge environment to a new, high-end cloud environment to provide fast and accurate predictions for accelerator implementation.
Interpreting Robustness Proofs of Deep Neural Networks
In recent years numerous methods have been developed to formally verify the robustness of deep neural networks (DNNs).
Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning
We leverage a general framework and find conditions to ensure efficient attack under a general assumption of the learning algorithms.
Efficient Two-Phase Offline Deep Reinforcement Learning from Preference Feedback
Our method ignores such state-actions during the second learning phase to achieve higher learning efficiency.
RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations
For training from scratch, \textbf{RAMP} achieves SOTA union accuracy of $44. 6\%$ and relatively good clean accuracy of $81. 2\%$ on ResNet-18 against AutoAttack on CIFAR-10.
Reward Poisoning Attack Against Offline Reinforcement Learning
To the best of our knowledge, we propose the first black-box reward poisoning attack in the general offline RL setting.
QuaCer-C: Quantitative Certification of Knowledge Comprehension in LLMs
Large Language Models (LLMs) have demonstrated impressive performance on several benchmarks.
