Welcome to the Secure, Trustworthy, and Reliable AI (Star-AI) Lab.
At Star-AI (★AI) Lab, we focus on cutting-edge research to make the online space safer.
To this end, we develop novel methods in three key areas: AI-enabled cybersecurity, Security of AI, and Privacy of AI. Please see our current projects and publications in each area from our team 😊 .
Recent News
- Our paper, Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement was accepted to NeurIPS 2024.
- Our paper, Learning Contextualized Action Representations in Sequential Decision Making for Adversarial Malware Optimization was accepted to TDSC 2024.
- Our paper, Efficient Secure Aggregation for Privacy-Preserving Federated Machine Learning was accepted to ACSAC 2024.
- Reza serves as a PC member in IEEE S&P Workshop on Deep Learning Security and Privacy 2023 .
- Reza helps organize IEEE ICDM Workshop on Machine Learning for Cybersecurity (MLC) 2023 .
- Our paper, Heterogeneous Domain Adaptation with Deep Adversarial Representation Learning: Experiments on E-Commerce and Cybersecurity was accepted to IEEE TPAMI 2022.
- Our paper, Counteracting Dark Web Text-Based CAPTCHA with Generative Adversarial Learning for Proactive Cyber Threat Intelligence was accepted to ACM TMIS 2022.
- Our paper, Single-Shot Black-Box Adversarial Attacks Against Malware Detectors: A Causal Language Model Approach was accepted to IEEE ISI 2021.
- Our paper on Deep Learning-based Privacy Awareness received the Best Paper Award in IEEE ISI 2021.
- Reza serves as Program Committee (PC) Member in IEEE S&P Workshop on Deep Learning and Security (DLS) 2022.
- Our paper, on Binary Black-Box Attacks Against Static Malware Detectors with Reinforcement Learning in Discrete Action Spaces was accepted at IEEE S&P Workshop on Deep Learning and Security (DLS) 2021.
- Our paper, Binary Black-box Evasion Attacks Against Deep Learning-based Static Malware Detectors with Adversarial Byte-Level Language Model was accepted to the AAAI Conference on Artificial Intelligence, Workshop on Robust, Secure, and Efficient Machine Learning (RSEML), 2021.
- Our Paper on Adversarial Cross-Lingual Knowledge Transfer in Hacker Forums was accepted at IEEE S&P Workshop on Deep Learning and Security (DLS).
