Amir Rahmati
Amir Rahmati

Assistant Professor

About Me

Amir Rahmati /æ’mi:r ræh’mæti/ (written as امیر رحمتی in Persian) is an Assistant Professor in the Department of Computer Science at Stony Brook University. He is the director of Ethos Security and Privacy lab and a member of Stony Brook National Security Institute. Amir’s research broadly focuses on system security. He is particularly interested in the security and privacy challenges of emerging technologies, including IoT, AR, and ML systems.

Teaching
Research
I lead the Ethos lab at Stony Brook University. In Ethos lab, we focus on improving the security of emerging technologies, such as Internet of Things (IoT) devices and Cyber-Physical systems. Our work involves designing, building, and evaluating systems that tackle security challenges in these domains. As we move towards a world where many resource- and energy-limited devices have access to our data & activities, our research creates an avenue for these devices to incorporate security in their design.
Prospective Students
I am looking for students with diverse backgrounds and expertise to work on challenging research problems across the system stack.
  • Do you like designing and developing elegant systems that tackle real-world problems?
  • Do you have expertise in hardware, software, machine learning, UX, or network protocols and measurement?
  • Are you passionate about security and privacy?
If your answer to these questions is yes, there may be a place for you in my group.

Interested? Fill out this form and tell me about yourself. Then, apply to our graduate program.

Publications
(2024). Security Analysis of RL-Based Artificial Pancreas Systems. In ACM HealthSec Workshop (HealthSec).
(2024). Fast Koopman Surrogate Falsification using Linear Relaxations and Weights. In International Symposium on Automated Technology for Verification and Analysis (ATVA).
(2024). Biosignal Authentication Considered Harmful Today. In USENIX Security Symposium (USENIX Sec).
(2024). Zero-One Attack: Degrading Closed-Loop Neural Network Control Systems using State-Time Perturbations. In International Conference on Cyber-Physical Systems (ICCPS).
(2024). Falsification using Reachability of Surrogate Koopman Models. In ACM International Conference on Hybrid Systems: Computation and Control (HSCC).
(2024). A Study of the Effects of Transfer Learning on Adversarial Robustness. In Transactions on Machine Learning Research (TMLR).
(2024). Like, Comment, Get Scammed: Characterizing Comment Scams on Media Platforms. In Network and Distributed System Security Symposium (NDSS).
(2023). Provable Observation Noise Robustness for Neural Network Control Systems. In Research Directions: Cyber-Physical Systems.
(2023). Erebus: Access Control for Augmented Reality Systems. In USENIX Security Symposium (USENIX Sec).
(2023). Scan Me If You Can: Understanding and Detecting Unwanted Vulnerability Scanning. In The Web Conference (WWW).
(2023). Synthesizing Pareto-Optimal Signal-Injection Attacks on ICDs. In IEEE Access (ACCESS).
(2022). Accelerating Certified Robustness Training via Knowledge Transfer. In Conference on Neural Information Processing Systems (NeurIPS).
(2022). On the Feasibility of Compressing Certifiably Robust Neural Networks. In Trustworthy and Socially Responsible Machine Learning (TSRML).
(2022). Transferring Adversarial Robustness Through Robust Representation Matching. In USENIX Security Symposium (USENIX Sec).
(2022). Ares: A System-Oriented Wargame Framework for Adversarial ML. In IEEE Deep Learning And Security Workshop (DLS).
(2021). Good Bot, Bad Bot: Characterizing Automated Browsing Activity. In IEEE Symposium on Security and Privacy (S&P).
(2020). An Intent-Based Automation Framework for Securing Dynamic Consumer IoT Infrastructures. In The Web Conference (WWW).
(2020). Valve: Securing Function Workflows on Serverless Computing Platforms. In The Web Conference (WWW).
(2020). Can Attention Masks Improve Adversarial Robustness?. In The AAAI-20 Workshop on Engineering Dependable and Secure Machine Learning Systems (EDSMLS).
(2019). Protecting Visual Information in Augmented Reality from Malicious Application Developers. In ACM Workshop on Wearable Systems and Applications (WearSys).
(2018). ATtention Spanned: Comprehensive Vulnerability Analysis of AT Commands Within the Android Ecosystem. In USENIX Security Symposium (USENIX Sec).
(2018). The State of Physical Attacks on Deep Learning Systems. In USENIX Summit on Hot Topics in Security (HotSec).
(2018). Physical Adversarial Examples for Object Detectors. In USENIX Workshop on Offensive Technologies (WOOT).
(2018). Robust Physical-World Attacks on Deep Learning Visual Classification. In Workshop on the Bright and Dark Sides of Computer Vision (CV-COPS).
(2018). Robust Physical-World Attacks on Deep Learning Visual Classification. In Conference on Computer Vision and Pattern Recognition (CVPR).
(2018). Caterpillar: Iterative Concolic Execution for Stateful Programs. In International KLEE Workshop on Symbolic Execution (KLEE).
(2018). Decentralized Action Integrity for Trigger-Action IoT Platforms. In Network and Distributed System Security Symposium (NDSS).
(2017). IFTTT vs. Zapier: A Comparative Study of Trigger-Action Programming Frameworks. In arXiv (1709.02788).
(2017). Heimdall: A Privacy-Respecting Implicit Preference Collection Framework. In ACM International Conference on Mobile Systems, Applications, and Services (MobiSys).
(2017). Internet of Things Security Research: A Rehash of Old Ideas or New Intellectual Challenges?. In IEEE Security & Privacy (S&P Magazine): Systems Attacks and Defenses.
(2017). Securing Trigger-Action Platforms. In USENIX Summit on Hot Topics in Security (HotSec).
(2017). Tyche: A Risk-Based Permission Model for Smart Homes. In IEEE Cybersecurity Development Conference (SecDev).
(2017). Support for Security and Safety of Programmable IoT Systems. In ISSTA Workshop on Testing Embedded and Cyber-Physical Systems (TECPS).
(2017). The Security Implications of Permission Models of Smart Home Application Frameworks. In IEEE Security & Privacy (S&P Magazine), Volume 15, Issue 2.
(2017). ContexIoT: Towards Providing Contextual Integrity to Appified IoT Platforms. In Network and Distributed System Security Symposium (NDSS).
(2016). Towards Comprehensive Repositories of Opinions. In ACM Workshop on Hot Topics in Networks (HotNets).
(2016). Applying the Opacified Computation Model to Enforce Information Flow Policies in IoT Applications. In IEEE Cybersecurity Development Conference (SecDev).
(2016). FlowFence: Practical Data Protection for Emerging IoT Application Frameworks. In USENIX Security Symposium (USENIX Sec).
(2016). Persistent Clocks for Batteryless Sensing Devices. In Transactions on Embedded Computing Systems (TECS).
(2016). Approximate Flash Storage: A Feasibility Study. In Workshop on Approximate Computing Across the Stack (WAX).
(2015). Context-Specific Access Control: Conforming Permissions With User Expectations. In ACM CCS Workshop on Security and Privacy in Smartphones and Mobile Devices (SPSM).
(2015). Probable Cause: The Deanonymizing Effects of Approximate DRAM. In International Symposium on Computer Architecture (ISCA).
(2014). Malware Prognosis: How to Do Malware Research in Medical Domain. In USENIX Workshop on Health Information Technologies (Health Tech).
(2014). Stigmalware: Investigating the Prevalence of Malware in the Clinical Domain. In Poster and Short Talk session of IEEE Symposium on Security and Privacy (IEEE S&P).
(2014). Reliable Physical Unclonable Functions using Data Retention Voltage of SRAM Cells. In IEEE Transactions on CAD: Special Section on Hardware Security and Trust (TCAD).
(2014). Refreshing Thoughts on DRAM: Power Saving vs. Data Integrity. In Workshop on Approximate Computing Across the System Stack (WACAS).
(2013). Under What Circumstances Are Insider Leaks Justified?. In Cyber Conflict Report.
(2013). Cyber Dimensions of State Repression. In Cyber Conflict Report.
(2013). WattsUpDoc: Power Side Channels to Nonintrusively Discover Untargeted Malware on Embedded Medical Devices. In USENIX Workshop on Health Information Technologies (Health Tech).
(2012). DRV-Fingerprinting: Using Data Retention Voltage of SRAM Cells for Chip Identification. In Workshop On RFID Security And Privacy (RFIDsec).
(2012). TARDIS: Secure Time Keeping For Embedded Devices Without Clocks. In Poster and Short Talk session of IEEE Symposium on Security and Privacy (IEEE S&P).
(2012). TARDIS: Time and Remanence Decay in SRAM to Implement Secure Protocols on Embedded Devices without Clocks. In USENIX Security Symposium (USENIX Sec).