Search Results for author:
Found 13 papers, 6 papers with code
Min-Max Optimization without Gradients: Convergence and Applications to Black-Box Evasion and Poisoning Attacks
In this paper, we study the problem of constrained min-max optimization in a black-box setting, where the desired optimizer cannot access the gradients of the objective function but may query its values.
Sign Bits Are All You Need for Black-Box Attacks
Similar performance is observed on a standard IMAGENET model with an average of $579$ queries.
Min-Max Optimization without Gradients: Convergence and Applications to Adversarial ML
In this paper, we study the problem of constrained robust (min-max) optimization ina black-box setting, where the desired optimizer cannot access the gradients of the objective function but may query its values.
There are No Bit Parts for Sign Bits in Black-Box Attacks
We present a black-box adversarial attack algorithm which sets new state-of-the-art model evasion rates for query efficiency in the $\ell_\infty$ and $\ell_2$ metrics, where only loss-oracle access to the model is available.
Lipizzaner: A System That Scales Robust Generative Adversarial Network Training
GANs are difficult to train due to convergence pathologies such as mode and discriminator collapse.
Multivariate Time-series Similarity Assessment via Unsupervised Representation Learning and Stratified Locality Sensitive Hashing: Application to Early Acute Hypotensive Episode Detection
Timely prediction of clinically critical events in Intensive Care Unit (ICU) is important for improving care and survival rate.
AST-Based Deep Learning for Detecting Malicious PowerShell
With the celebrated success of deep learning, some attempts to develop effective methods for detecting malicious PowerShell programs employ neural nets in a traditional natural language processing setup while others employ convolutional neural nets to detect obfuscated malicious commands at a character level.
Towards Distributed Coevolutionary GANs
Generative Adversarial Networks (GANs) have become one of the dominant methods for deep generative modeling.
On Visual Hallmarks of Robustness to Adversarial Malware
A central challenge of adversarial learning is to interpret the resulting hardened model.
Approximating Nash Equilibria for Black-Box Games: A Bayesian Optimization Approach
Game theory has emerged as a powerful framework for modeling a large range of multi-agent scenarios.
Computer Science and Game Theory
Adversarial Deep Learning for Robust Detection of Binary Encoded Malware
We are inspired by them to develop similar methods for the discrete, e. g. binary, domain which characterizes the features of malware.
Embedded Bandits for Large-Scale Black-Box Optimization
In essence, the EmbeddedHunter algorithm expands optimistically a partitioning tree over a low-dimensional---equal to the effective dimension of the problem---search space based on a bounded number of random embeddings of sampled points from the low-dimensional space.
BMOBench: Black-Box Multi-Objective Optimization Benchmarking Platform
This document briefly describes the Black-Box Multi-Objective Optimization Benchmarking (BMOBench) platform.
