Session

· Contributors · Organizations · Search Program · Flagged · Happening Now

Research Manuscript: Glitz, Glam, and Binary Jam: A Symphony of New Security Trends for Deep Neural Networks

Session Chair

DescriptionThis session takes you through cutting-edge AI defenses: Explore novel strategies defending against adversarial examples, patches, and addressing privacy/IP concerns. Witness the fusion of technology and time, leveraging device aging to combat attacks. Dive into innovative watermarking frameworks and victim-focused defenses, strengthening DNNs' and LLMs' security. Join us in this AI Safeguard Showcase, revealing crucial insights into the dynamic universe of AI security and privacy. A condensed exploration of the future of AI defense awaits!

Event TypeResearch Manuscript

TimeWednesday, June 263:30pm - 5:30pm PDT

Location3002, 3rd Floor

Topics

Keywords

Presentations

3:30pm - 3:45pm PDT	TBNet: A Neural Architectural Defense Framework Facilitating DNN Model Protection in Trusted Execution Environments Authors Ziyu Liu Tong Zhou Yukui Luo Xiaolin Xu
3:45pm - 4:00pm PDT	Older and Wise: The Marriage of Device Aging and Intellectual Property Protection of DNNs Authors Ning Lin Shaocong Wang Yue Zhang Yangu He Kwunhang Wong Arindam Basu Dashan Shang Xiaoming Chen Zhongrui Wang
4:00pm - 4:15pm PDT	QMark: Robust Watermarks for IP Protection of Quantized Large Language Models Authors Ruisi Zhang Farinaz Koushanfar
4:15pm - 4:30pm PDT	AdvHunter: Detecting Adversarial Perturbations in Black-Box Neural Networks through Hardware Performance Counters Authors Manaar Alam Michail Maniatakos
4:30pm - 4:45pm PDT	DNN-Defender: A Victim-Focused In-DRAM Defense Mechanism for Taming Adversarial Weight Attack on DNNs Authors Ranyang Zhou Sabbir Ahmed Adnan Siraj Rakin Shaahin Angizi
4:45pm - 5:00pm PDT	Defending against Adversarial Patches using Dimensionality Reduction Authors Nandish Chattopadhyay Amira Guesmi Muhammad Abdullah Hanif Bassem Ouni Muhammad Shafique
5:00pm - 5:15pm PDT	EOS: An Energy-Oriented Attack Framework for Spiking Neural Networks Authors Ning Yang Fangxin Liu Zongwu Wang Haomin Li Zhuoran Song Songwen Pei
5:15pm - 5:30pm PDT	FastQuery: Communication-efficient Embedding Table Query for Private LLMs inference Authors Chenqi Lin Tianshi Xu Zebin Yang Meng Li Runsheng Wang Ru Huang

DAC 2024