Search Results for author:
Found 6 papers, 1 papers with code
Handling Adversarial Concept Drift in Streaming Data
While traditional partially labeled concept drift detection methodologies fail to detect adversarial drifts, the proposed framework is able to detect such drifts and operates with <6% labeled data, on average.
Security Theater: On the Vulnerability of Classifiers to Exploratory Attacks
The adversary assumes a black box model of the defender's classifier and can launch indiscriminate attacks on it, without information of the defender's model type, training data or the domain of application.
A Dynamic-Adversarial Mining Approach to the Security of Machine Learning
While most works in the security of machine learning has concentrated on the evasion resistance (a) problem, there is little work in the areas of reacting to attacks (b and c).
On the Reliable Detection of Concept Drift from Streaming Unlabeled Data
On the other hand, unsupervised change detection techniques are unreliable, as they produce a large number of false alarms.
Evaluating Complex Task through Crowdsourcing: Multiple Views Approach
However, for getting grades for complex tasks, which require specific skills and efforts for grading, crowdsourcing encounters a restriction of insufficient knowledge of the workers from the crowd.
Data Driven Exploratory Attacks on Black Box Classifiers in Adversarial Domains
In this paper, an adversary's view point of a classification based system, is presented.
