Data poisoning is an attack on machine learning models wherein the attacker adds examples
to the training set to manipulate the behavior of the model at test time. This paper explores …

Little is known about the duration and prevalence of zero-day attacks, which exploit vulnerabilities
that have not been disclosed publicly. Knowledge of new vulnerabilities gives cyber …

In recent years, the number of software vulnerabilities discovered has grown significantly.
This creates a need for prioritizing the response to new disclosures by assessing which …

… Our attack consists of selecting base instances that are close to the target t in deep feature
space, but are labeled by the oracle as the attacker’s desired label yd. CRAFTINSTANCE cre…

We characterize a prevalent weakness of deep neural networks (DNNs),’overthinking’,
which occurs when a DNN can reach correct predictions before its final layer. Overthinking is …

The fast evolution pace for cloud computing software is on a collision course with our growing
reliance on cloud computing. On one hand, cloud software must have the agility to evolve …

Deep neural networks (DNNs) have been shown to tolerate" brain damage": cumulative
changes to the network's parameters (eg, pruning, numerical perturbations) typically result in a …

… Right-censoring and lefttruncation are well studied in statistics, and in this paper we
compute the values of S(t) using the Kaplan-Meier estimator, which accounts for truncated and …

… 11.4 t 1.1 … [7] T. Dumitras, and D. Shou. Toward a standard benchmark for computer
security research: The Worldwide Intelligence Network Environment (WINE). …

Malware detection increasingly relies on machine learning techniques, which utilize
multiple features to separate the malware from the benign apps. The effectiveness of these …