Latest
- Training Robust ML-based Raw-Binary Malware Detectors in Hours, not Months
- Harmful Bias: A General Label-Leakage Attack on Federated Learning from Bias Gradients
- The Ultimate Combo: Boosting Adversarial Example Transferability by Composing Data Augmentations
- Privacy-Preserving Collaborative Genomic Research: A Real-Life Deployment and Vision
- A High Coverage Cybersecurity Scale Predictive of User Behavior
- CaFA: Cost-aware, Feasible Attacks With Database Constraints Against Neural Tabular Classifiers
- DrSec: Flexible Distributed Representations for Efficient Endpoint Security
- Group-based Robustness: A General Framework for Customized Robustness in the Real World
- Accessorize in the Dark: A Security Analysis of Near-Infrared Face Recognition
- Adversarial Training for Raw-Binary Malware Classifiers
- Property-Driven Evaluation of RL-Controllers in Self-Driving Datacenters
- Scalable Verification of GNN-based Job Schedulers
- "I Have No Idea What a Social Bot Is": On Users' Perceptions of Social Bots and Ability to Detect Them
- Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks
- Malware Makeover: Breaking ML-based Static Analysis by Modifying Executable Bytes
- How Risky Are Real Users' IFTTT Applets?
- Training Older Adults to Resist Scams with Fraud Bingo and Scam-Detection Challenges
- $n$-ML: Mitigating Adversarial Examples via Ensembles of Topologically Manipulated Classifiers
- A General Framework for Adversarial Examples with Objectives
- A Field Study of Computer-Security Perceptions Using Anti-Virus Customer-Support Chats
- Comparing Hypothetical and Realistic Privacy Valuations
- Predicting Impending Exposure to Malicious Content from User Behavior
- On the Suitability of $L_p$-norms for Creating and Preventing Adversarial Examples
- Riding Out DOMsday: Toward Detecting and Preventing DOM Cross-Site Scripting
- Topics of Controversy: An Empirical Analysis of Web Censorship Lists
- Self-Confidence Trumps Knowledge: A Cross-Cultural Study of Security Behavior
- Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition
- (Do Not) Track Me Sometimes: Users' Contextual Preferences for Web Tracking