{"685448":{"#nid":"685448","#data":{"type":"event","title":"PhD Proposal  by Jianming Tong","body":[{"value":"\u003Cp\u003ETitle:\u0026nbsp;\u003Cstrong\u003E Efficient Reconfigurable Privacy-Preserving AI\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EDate: Tuesday, \u003Cstrong\u003EOct 8, 2025\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003ETime: \u003Cstrong\u003E9:00 AM \u2013 11:00 AM ET\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003ELocation: Remote\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;Zoom Meeting:\u0026nbsp;\u003Ca href=\u0022https:\/\/gatech.zoom.us\/my\/jianming\u0022 title=\u0022https:\/\/gatech.zoom.us\/my\/jianming\u0022\u003Ehttps:\/\/gatech.zoom.us\/my\/jianming\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ECommittee:\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EDr. Tushar Krishna (Advisor) - ECE, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003EDr. Hyesoon Kim - CS, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003EDr. Moinuddin Qureshi\u0026nbsp;- CS, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003EDr. G.\u0026nbsp;Edward Suh\u0026nbsp;- ECE, Cornell University \/ NVIDIA\u003C\/p\u003E\u003Cp\u003EDr. Srini Devadas - EECS, Massachusetts Institute of Technology\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EAbstract:\u003C\/strong\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe current trajectory of AI systems prioritizes computational performance at scale, often relegating data privacy to an afterthought. This approach is unsustainable. The imminent rise of personalized agents, embodied AI, and sensitive applications like healthcare transforms privacy from a mere compliance feature into a fundamental requirement for earning user trust and ensuring market viability. This creates a critical bottleneck for current systems: how do we secure AI of tomorrow using the non-private infrastructure we have today?\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EModern large-scale privacy-preserving machine learning (PPML) systems often rely on a hardware-centric solution, designing Trusted Execution Environments (TEEs) for every system component (CPU, GPU, memory and communication etc.). It introduces disjointed development and maintenance costs. This thesis\u0026nbsp;is to bring all levels of privacy protection to existing AI systems and understand principles of privacy protection for improving efficiency. This brings two benefits: (a) immediate augmentation of existing AI systems with all levels of privacy protection without hardware changes, and (b) guidance on the design of future reconfigurable AI systems that can adapt itself to efficiently serve both full-spectrum PPML and standard ML. My research enables it via full-stack optimizations on four pillars: (1) ML model architecture that isolates private assets into separate independent routes by design, controlling how much data requires protection, (2) Privacy preservation that leverages domain-specific knowledge to minimize the extra costs introduced by privacy guarantee, (3) Compilation that lowers high-precision modular cryptographic operators across privacy tiers into low-precision kernels efficient on today\u2019s hardware, and (4) Hardware that reconfigures itself to efficiently process computation of various shapes and flexible memory reorganizations.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003E\u003Cstrong\u003EEfficient Reconfigurable Privacy-Preserving AI\u003C\/strong\u003E\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Efficient Reconfigurable Privacy-Preserving AI"}],"uid":"27707","created_gmt":"2025-10-01 19:08:24","changed_gmt":"2025-10-01 19:08:24","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2025-10-08T09:00:00-04:00","event_time_end":"2025-10-08T11:00:00-04:00","event_time_end_last":"2025-10-08T11:00:00-04:00","gmt_time_start":"2025-10-08 13:00:00","gmt_time_end":"2025-10-08 15:00:00","gmt_time_end_last":"2025-10-08 15:00:00","rrule":null,"timezone":"America\/New_York"},"location":"REMOTE","extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"102851","name":"Phd proposal"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}