Large Language Models (LLMs) have shown promise in automated program
rea...
ML models are increasingly being pushed to mobile devices, for low-laten...
Existing defense methods against adversarial attacks can be categorized ...
Machine learning models often fail on out-of-distribution (OOD) samples....
Machine learning (ML) models can leak information about users, and
diffe...
Pretrained large-scale vision-language models like CLIP have exhibited s...
Despite their excellent performance, state-of-the-art computer vision mo...
Many visual recognition models are evaluated only on their classificatio...
Deep networks for computer vision are not reliable when they encounter
a...
It is beneficial to develop an efficient machine-learning based method f...
Determining whether multiple instructions can access the same memory loc...
Visual representations underlie object recognition tasks, but they often...
Full-precision deep learning models are typically too large or costly to...
Deep networks achieve state-of-the-art performance on computer vision ta...
We find that images contain intrinsic structure that enables the reversa...
Demand for enterprise data warehouse solutions to support real-time Onli...
The overhead of the kernel storage path accounts for half of the access
...
We introduce a framework for learning robust visual representations that...
Detecting semantically similar functions – a crucial analysis capability...
Feature extraction with convolutional neural networks (CNNs) is a popula...
Accurate and robust disassembly of stripped binaries is challenging. The...
Although deep networks achieve strong accuracy on a range of computer vi...
Like all software systems, the execution of deep learning models is dict...
Semantic segmentation is one of the most impactful applications of machi...
Deep networks are well-known to be fragile to adversarial attacks. Using...
Neural networks are increasingly deployed in real-world safety-critical
...
Fuzzing has become the de facto standard technique for finding software
...
Effective overload control for large-scale online service system is cruc...
Due to the increasing deployment of Deep Neural Networks (DNNs) in real-...
Due to the increasing usage of machine learning (ML) techniques in secur...
Today's monolithic kernels often implement a small, fixed set of policie...