BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CECS - ECPv6.18.4//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://www.cecs.uci.edu
X-WR-CALDESC:Events for CECS
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20240310T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20241103T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20250309T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20251102T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20260308T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20261101T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;VALUE=DATE:20250506
DTEND;VALUE=DATE:20250510
DTSTAMP:20250404T180356Z
CREATED:20250403T192124Z
LAST-MODIFIED:20250404T180356Z
UID:16421-1746489600-1746835199@www.cecs.uci.edu
SUMMARY:Cyber-Physical Systems and Internet-of-Things (CPS-IoT) Week 2025
DESCRIPTION:CPS-IoT Week is the premier event on Cyber-Physical Systems and the Internet-of-Things. It brings together four top conferences\, multiple workshops\, tutorials\, and competition. This year\, CECS is thrilled to host CPS-IoT Week 2025 at the UC Irvine Student Center! \n  \nConferences: \n\nHSCC – 28th ACM International Conference on Hybrid Systems: Computation and Control\nICCPS – 16th ACM/IEEE International Conference on Cyber-Physical Systems\nSenSys – 23rd ACM Conference on Embedded Networked Sensor Systems\nRTAS – 31st IEEE Real-Time and Embedded Technology and Applications Symposium\n\n  \nWorkshops: \n\nThe 2nd International Workshop on Foundation Models for Cyber-Physical Systems & Internet of Things (FMSys)\nThe 2nd International Workshop on Security and Privacy of Sensing Systems (Sensors S&P)\nThe 4th International Workshop on Real-time and IntelliGent Edge computing (RAGE)\nThe 5th Workshop on Computation-Aware Algorithmic Design for Cyber-Physical Systems\nThe 1st Workshop on Modeling and Verification for Secure and Performant Cyber-Physical Systems (MoVe4SPS)\nThe 3rd International Workshop on Human-Centered Sensing\, Modeling\, and Intelligent Systems (HumanSys)\nThe 1st Workshop on Formal Arguments for Cps CerTification (FACCT)\nThe 13th International Workshop on Energy Harvesting and Energy-Neutral Sensing Systems (ENSsys)\nThe 7th Workshop on Design Automation for CPS and IoT (DESTION)\n\n  \nTutorials: \n\nSafe Building App Deployments in Three Easy Steps with Brick and Playground\nFormal Verification and Control with Conformal Prediction\nAligning Ethics and CPS/IoT\nScenic: An Open-Source Probabilistic Programming System for Data Generation and Safety in AI-Based Autonomy\nGoing Public with Your CPS Code and Data\n\n  \nCompetition: \n\nThe 4th Student Design Competition on Networked Computing on the Edge\n\n  \nLearn more at the CPS-IoT Week website.
URL:https://www.cecs.uci.edu/event/cyber-physical-systems-and-internet-of-things-cps-iot-week-2025/
LOCATION:Student Center\, 311 W Peltason Dr\, Irvine\, CA\, 92697\, United States
CATEGORIES:Other Events
ATTACH;FMTTYPE=image/jpeg:https://cecs.uci.edu/files/2025/04/220315_Studentcenter-scaled.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20250514T110000
DTEND;TZID=America/Los_Angeles:20250514T120000
DTSTAMP:20250513T184214Z
CREATED:20250512T171811Z
LAST-MODIFIED:20250513T184214Z
UID:16450-1747220400-1747224000@www.cecs.uci.edu
SUMMARY:In-Memory Computing to Accelerate Machine Learning
DESCRIPTION:Name: Mariam Rakka \nChair: Prof. Fadi Kurdahi \nDate: May 14\, 2025 \nTime: 11:00 AM \nLocation: EH 2430 \nCommittee: Prof. Nikil Dutt\, Prof. Rainer Döemer \nTitle: In-Memory Computing to Accelerate Machine Learning \nAbstract: The increasing computational demands of Machine Learning (ML) models have made conventional computing architectures inadequate due to energy inefficiencies and data movement bottlenecks. In-memory computing (IMC) offers a promising alternative by enabling computation directly within memory arrays. This dissertation presents novel architectural and algorithmic strategies to accelerate machine learning inference using IMC. It proposes precision-fluid data flows and hardware/software co-design techniques to efficiently accelerate different ML workloads. Performance evaluations demonstrate that IMC-based designs can deliver substantial improvements in energy efficiency and throughput\, making them viable candidates for next-generation AI systems. \nBio: Mariam Rakka received her B.E. degree in Computer and Communications Engineering with high distinction from the American University of Beirut\, Lebanon\, in 2020\, along with two minors in Mathematics and Business Administration. She received her M.S. degree in Electrical and Computer Engineering from the University of California\, Irvine\, in 2022. She is currently pursuing her Ph.D. degree in Electrical and Computer Engineering at the University of California\, Irvine under the mentorship of Professor Fadi J. Kurdahi. Her research interests include systems for machine learning and hardware/software co-design. She has completed research internships at Arm in 2022\, 2023\, and 2024\, where she contributed to the design of future generations of ARM processors. She has published in top-tier journals and conferences and served as a reviewer for several peer-reviewed journals in the field.
URL:https://www.cecs.uci.edu/event/in-memory-computing-to-accelerate-machine-learning/
LOCATION:EH 2430\, Engineering Hall\, University of California\, Irvine\, Irvine\, CA\, 92697\, United States
CATEGORIES:PhD Defenses
ATTACH;FMTTYPE=image/jpeg:https://cecs.uci.edu/files/2025/05/mariam_rakka.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20250519T110000
DTEND;TZID=America/Los_Angeles:20250519T120000
DTSTAMP:20250513T184038Z
CREATED:20250513T183835Z
LAST-MODIFIED:20250513T184038Z
UID:16459-1747652400-1747656000@www.cecs.uci.edu
SUMMARY:Efficient and Robust Defense against Query-based Black-box Attacks
DESCRIPTION:Title: Efficient and Robust Defense against Query-based Black-box Attacks \nSpeaker: Shaofei Li \nDate and Time: Monday\, May 2119\, 11:00am \nLocation: EH 2430 \nAbstract: \nQuery-based black-box attacks have emerged as a significant threat to machine learning systems\, where adversaries can manipulate the input queries to generate adversarial examples that can cause misclassification of the system. To counter these attacks\, researchers have proposed Stateful Defense Models (SDMs) such as BlackLight and PIHA\, which can reject queries that are “similar” to historical queries. However\, recent studies show that existing approaches are vulnerable to a stronger adaptive attack\, Oracle-guided Adaptive Rejection Sampling (OARS). OARS can be easily integrated with existing attack algorithms to evade the SDMs by generating queries with fine-tuned direction and step size of perturbations utilizing the leaked decision boundary from the SDMs. In this talk\, I will present our novel approach\, Query Provenance Analysis (QPA)\, for defending against query-based black-box attacks robustly (against both non-adaptive and adaptive attacks) and efficiently (in real-time). The key insight is that\, instead of focusing on individual queries\, utilizing features from the query sequence (termed query provenance) can distinguish malicious queries from benign queries more effectively. So it constructs a query provenance graph to capture the relationship between a new query and prior historical queries\, and then design efficient algorithms to detect malicious queries based on the query provenance graphs. As a results\, QPA outperforms the baselines regarding defense robustness and efficiency on both non-adaptive and adaptive attacks. It can also be deployed for various attack scenarios\, such as membership inference attack and jailbreaking. \nBiography: \nShaofei Li is currently a fourth-year Ph.D. student in the Department of Computer Science at Peking University\, advised by Prof. Ding Li\, Prof. Yao Guo and Prof. Xiangqun Chen. He received his B.S. degree from the School of Electronics Engineering and Computer Science (EECS) at Peking University in 2021. His research interests lie in cybersecurity\, system security and AI security. His research focuses on developing detection and defense mechanisms for various security threats in the real world systems. He has published several papers in top-tier security conferences and transactions such as S&P\, NDSS\, CCS and TOSEM. More information can be found at his website: https://shaofei-li.org/ \nHosted By: Prof. Zhou Li \nMore Information
URL:https://www.cecs.uci.edu/event/efficient-and-robust-defense-against-query-based-black-box-attacks/
LOCATION:EH 2430\, Engineering Hall\, University of California\, Irvine\, Irvine\, CA\, 92697\, United States
CATEGORIES:Seminars at CECS
ATTACH;FMTTYPE=image/jpeg:https://cecs.uci.edu/files/2025/05/shaofei_li.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20250519T110000
DTEND;TZID=America/Los_Angeles:20250519T120000
DTSTAMP:20250513T184743Z
CREATED:20250513T184624Z
LAST-MODIFIED:20250513T184743Z
UID:16468-1747652400-1747656000@www.cecs.uci.edu
SUMMARY:TEE-Shielded LLM Partition – Efficiently Protect Model Security on User Devices
DESCRIPTION:Title: TEE-Shielded LLM Partition – Efficiently Protect Model Security on User Devices \nSpeaker: Ziqi Zhang \nDate and Time: Monday\, May 19\, 11:00am \nLocation: EH 2430 \nAbstract: \nIn this talk\, I will introduce recent work on TEE-based LLM protection (TSLP) on the user devices: TEESlice (S&P24) and ArrowCloak (Security25 revision). Existing TEE products provides high security guarantee\, but usually lack GPU support and introduce additional inference latency. TSLP aims to incorporate untrusted GPU into TEE to reduce computation overhead. TSLP partition a LLM into two parts\, offloading the privacy-insensitive part to the GPU while shielding the critical privacy-sensitive part within the TEE. In TEESlice\, we systematically review and benchmark existing TSDP solutions and reveal that offloading model weights in plain-text leaks model privacy. Based on the observation\, TEESlice uses a partition-before-training strategy for accurate separation between privacy-related weights from public weights. In ArrowCloak\, we review existing lightweight weight obfuscation solutions in TSLP and find that these solutions cannot effectively protect vector direction in the weight matrix. We use a proof-of-concept attack to exploit this vulnerability and propose ArrowCloak that uses vector-matrix multiplication to protect vector direction. \nBiography: \nZiqi Zhang is currently a Postdoc Researcher at University of Illinois Urbane-Champaign\, working with Lingming Zhang. In 2023\, he obtained Ph.D degree in the School of Computer Science from Peking University in China. Before that\, he obtained the bachelor degree in the School of EECS of Peking University in 2018. His research interests lie in AI security\, software engineering\, and software security. His interested topics include trusted AI\, AI with trusted hardware\, and AI with SE. He has published several papers at top-tier conferences in various domains\, including computer security (S&P\, USENIX Security\, CCS)\, software engineering (ESEC/FSE\, ICSE\, ISSTA\, ISSRE)\, AI (ICML\, WWW)\, and ubiquitous computing (Ubicomp). More information can be found at https://ziqi-zhang.github.io/ \nHosted By: Prof. Zhou Li \nMore Information
URL:https://www.cecs.uci.edu/event/tee-shielded-llm-partition-efficiently-protect-model-security-on-user-devices/
LOCATION:EH 2430\, Engineering Hall\, University of California\, Irvine\, Irvine\, CA\, 92697\, United States
CATEGORIES:Seminars at CECS
ATTACH;FMTTYPE=image/png:https://cecs.uci.edu/files/2025/05/ziqi_zhang.png
END:VEVENT
END:VCALENDAR