BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260730T152637Z
LOCATION:
DTSTART;TZID=America/Los_Angeles:20260728T124800
DTEND;TZID=America/Los_Angeles:20260728T124800
UID:dac_DAC 2026_sess315_RESEARCH2832@linklings.com
SUMMARY:Nothing Left to Learn: Isomorphic Graph Transformations for Hardwa
 re IP Protection
DESCRIPTION:Shaza Elsharief (New York University, Abu Dhabi); Lilas Alrahi
 s (Khalifa University); and Johann Knechtel and Ozgur Sinanoglu (New York 
 University, Abu Dhabi)\n\nLogic locking protects hardware designs across t
 he global semicon-\nductor supply-chain. However, recent machine learning 
 (ML)-based\nattacks, especially graph learning-based ones, have undermined
 \nits security by learning circuit structures and gate compositions to\nre
 veal locked connections/gates. Although recent locking methods\nuse explai
 nability tools and adversarial perturbations, they remain\nvulnerable to M
 L attacks under robust training. Therefore, there is\nstill a need for tru
 ly learning-resilient locking solutions.\nWe propose IsoLock, a locking sc
 heme that performs intercon-\nnect obfuscation to secure the circuit's str
 ucture and functionality.\nIsoLock models the gate-level netlist as a grap
 h and introduces\nMUXes for locking (through rewiring selected interconnec
 ts), gen-\nerating isomorphic structures. These structures are indistingui
 sh-\nable to ML models and other structural attacks, effectively blocking\
 nall learnable/predictable features and preventing key deciphering.\nFor e
 valuation, first, we prove IsoLock's security against modeling\nattacks. S
 econd, we lock standard ISCAS-85 and ITC-99 benchmarks\nand evaluate them 
 against state-of-the-art ML attacks (SCOPE and\nMuxLink) and structural at
 tacks (Redundancy and SAAM), all of\nwhich can decipher only 0–6% of the c
 orrect key on average, con-\nfirming IsoLock's resilience also in practice
 .\n\nTopics: Quantum\n\nTrack: DES6. Quantum Computing, Systems\n\nSession
  Chairs: Hokeun Kim (Arizona State University); BaekGyu Kim (Daegu Gyeongb
 uk Institute of Science and Technology); Xiang Chen (Peking University); S
 angyeob Kim (Yonsei University); Robert M. Radway (University of Pennsylva
 nia); Prashanth Mohan (University of Pittsburgh); Xiaoxuan Yang (Universit
 y of Virginia, Stanford University); Ramtin Zand (University of South Caro
 lina); Hadi Kamali (University of Central Florida); Jiafeng Xie (Villanova
  University); Prabuddha Chakraborty (University of Maine); Junichiro Kadom
 oto (University of Tokyo); and Yosuke Ueno (RIKEN)\n\n
END:VEVENT
END:VCALENDAR