Latest

• Sy-FAR: Symmetry-based Fair Adversarial Robustness
• Backdooring Acoustic Foundation Models for Physically Realizable Triggers
• Reconstructing Template-Memorized Images from Natural Prompts
• How Probing for Problems and Bias Affects Perceptions of AI Chatbot Trustworthiness
• Universal Jailbreak Suffixes Are Strong Attention Hijackers
• NoisePrints: Distortion-Free Watermarks for Authorship in Private Diffusion Models
• Safeguarding Language Models via Self-Destruct Trapdoor
• Bot Among Us: Exploring User Awareness and Privacy Concerns About Chatbots in Group Chats
• GASLITEing the Retrieval: Exploring Vulnerabilities in Dense Embedding-based Search
• Safety Perceptions of Generative AI Conversational Agents: Uncovering Perceptual Differences in Trust, Risk, and Fairness
• On a Scale of 1 to 5, How Reliable Are AI User Studies? A Call for Developing Validated, Meaningful Scales and Metrics about User Perceptions of AI Systems
• 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