BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Penn Engineering Events - ECPv6.16.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Penn Engineering Events
X-ORIGINAL-URL:https://seasevents.nmsdev7.com
X-WR-CALDESC:Events for Penn Engineering Events
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250402T120000
DTEND;TZID=America/New_York:20250402T131500
DTSTAMP:20260602T114543
CREATED:20241118T151023Z
LAST-MODIFIED:20241118T151023Z
UID:12645-1743595200-1743599700@seasevents.nmsdev7.com
SUMMARY:ASSET Seminar: "Getting Lost in ML Safety Vibes"
DESCRIPTION:Abstract:  \nMachine learning applications are increasingly reliant on black-box pretrained models. To ensure safe use of these models\, techniques such as unlearning\, guardrails\, and watermarking have been proposed to curb model behavior and audit usage. Unfortunately\, while these post-hoc approaches give positive safety ‘vibes’ when evaluated in isolation\, our work shows that existing techniques are quite brittle when deployed as part of larger systems. In a series of recent works\, we show that: (a) small amounts of auxiliary data can be used to ‘jog’ the memory of unlearned models; (b) current unlearning benchmarks obscure deficiencies in both finetuning and guardrail-based approaches; and (c) simple\, scalable attacks erode existing LLM watermarking systems and reveal fundamental trade-offs in watermark design. Taken together\, these results highlight major deficiencies in the practical use of post-hoc ML safety methods. We end by discussing promising alternatives to ML safety\, which instead aim to ensure safety by design during the development of ML systems. \nZoom Link (if unable to attend in-person): https://upenn.zoom.us/j/91619533220
URL:https://seasevents.nmsdev7.com/event/asset-seminar-virginia-smith-carnegie-mellon-university/
LOCATION:Amy Gutmann Hall\, Room 414\, 3333 Chestnut Street\, Philadelphia\, 19104\, United States
END:VEVENT
END:VCALENDAR