Source Themes

Accessorize in the Dark: A Security Analysis of Near-Infrared Face Recognition

Prior work showed that face-recognition systems ingesting RGB images captured via visible-light (VIS) cameras are susceptible to real-world evasion attacks. Face-recognition systems in near-infrared (NIR) are widely deployed for critical tasks (e.g., …

Adversarial Training for Raw-Binary Malware Classifiers

Machine learning (ML) models have shown promise in classifying raw executable files (binaries) as malicious or benign with high accuracy. This has led to the increasing influence of ML-based classification methods in academic and real-world malware …

Property-Driven Evaluation of RL-Controllers in Self-Driving Datacenters

Reinforcement learning-based controllers (RL-controllers) in self-driving datacenters have evolved into complex dynamic systems that require continuous tuning to achieve higher performance than hand-crafted expert heuristics. The operating …

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. Despite their impressive performance, concerns remain over whether these GNN-based job schedulers …

"I Have No Idea What a Social Bot Is": On Users' Perceptions of Social Bots and Ability to Detect Them

Social bots—software agents controlling accounts on online social networks (OSNs)—have been employed for various malicious purposes, including spreading disinformation and scams. Understanding user perceptions of bots and ability to distinguish them …

Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks

Minimal adversarial perturbations added to inputs have been shown to be effective at fooling deep neural networks. In this paper, we introduce several innovations that make white-box targeted attacks follow the intuition of the attacker's goal: to …

Malware Makeover: Breaking ML-based Static Analysis by Modifying Executable Bytes

Motivated by the transformative impact of deep neural networks (DNNs) in various domains, researchers and anti-virus vendors have proposed DNNs for malware detection from raw bytes that do not require manual feature engineering. In this work, we …

How Risky Are Real Users' IFTTT Applets?

Smart-home devices are becoming increasingly ubiquitous and interconnected with other devices and services, such as phones, fitness trackers, cars, and social media accounts. Built-in connections between these services are still emerging, but …

Training Older Adults to Resist Scams with Fraud Bingo and Scam-Detection Challenges

Older adults are disproportionately affected by scams, many of which target them specifically. In this interactive demo, we present *Fraud Bingo*, an intervention designed by WISE & Healthy Aging Center in Southern California prior to 2012, that has …

$n$-ML: Mitigating Adversarial Examples via Ensembles of Topologically Manipulated Classifiers

This paper proposes a new defense called $n$-ML against adversarial examples, i.e., inputs crafted by perturbing benign inputs by small amounts to induce misclassifications by classifiers. Inspired by $n$-version programming, $n$-ML trains an …