BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.5//EN
TZID:America/Los_Angeles
X-WR-TIMEZONE:America/Los_Angeles
BEGIN:VEVENT
UID:0-1824@hmc.edu
DTSTART;TZID=America/Los_Angeles:20260925T110000
DTEND;TZID=America/Los_Angeles:20260925T120000
DTSTAMP:20260923T161705Z
URL:https://www.hmc.edu/calendar/events/cs-colloquium-from-prompts-to-sili
 con-security-and-privacy-threats-across-the-llm-stack-nael-abu-ghazaleh/
SUMMARY:CS Colloquium– “From Prompts to Silicon: Security and Privacy T
 hreats Across the LLM Stack\,” Nael Abu-Ghazaleh
DESCRIPTION:Large language models are now trusted with sensitive data\, emb
 edded in consequential decision pipelines\, and are hosted on shared\, exp
 ensive hardware. These factors make them an increasingly attractive target
 \, and not just at the level of what you type into a chat box. In this tal
 k\, we'll go on a tour of LLM security and privacy threats\, organized aro
 und a simple question\, looking at different classes of attacks based on a
 ttackers' access points.\n\nNael Abu-Ghazaleh starts where most people thi
 nk LLM security lives: at the prompt itself\, showing how attackers with m
 alicious intent can bypass the model’s safety training. A second group o
 f attacks targets training time\, where an attacker who controls even a sm
 all slice of a model's training data can plant hidden behaviors that surfa
 ce only later\, including those that enable leaking private information or
  undermining the safety alignment of the model. Finally\, Abu-Ghazaleh goe
 s below the model entirely\, to the hardware it runs on: his recent work s
 hows the GPU infrastructure powering today’s LLMs leaks information acro
 ss users who are supposed to be strongly isolated from each other. Taken t
 ogether\, these attacks show that LLM security isn’t one problem but sev
 eral\, spread across different layers of the stack\, including inference t
 ime\, training time\, and hardware and system vulnerabilities. Abu-Ghazale
 h closes with where he thinks the most promising defenses lie\, and the op
 en questions.\n\n\nSpeaker\nNael Abu-Ghazaleh is a professor in the Comput
 er Science and Engineering Department at the University of California\, Ri
 verside. His research is in architecture and system security\, and securit
 y for emerging systems. He has published over 250 papers in these areas\, 
 several of which have been recognized with best paper awards or nomination
 s. His offensive security research has resulted in the discovery of severa
 l new attacks on CPUs and GPUs that have been disclosed to companies inclu
 ding Intel\, AMD\, ARM\, Apple\, Microsoft\, Google and Nvidia\, and resul
 ted in patches and modifications to products\, and coverage from technical
  news outlets. He is a member of the Micro Hall of Fame\, an ACM distingui
 shed member\, an IEEE distinguished speaker and an IEEE Computer Society D
 istinguished Contributor.
CATEGORIES:Faculty,Staff,Students
LOCATION:Galileo Hall\, 240 Platt Blvd.\, Claremont\, CA\, 91711\, United S
 tates
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=240 Platt Blvd.\, Claremont
 \, CA\, 91711\, United States;X-APPLE-RADIUS=100;X-TITLE=Galileo Hall:geo:
 0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR