Close

Session

<
Research Manuscript
: Robust and Trusted AI Systems: Attacks, Defenses, and Hardware Reliability
Session Chairs
Jungwook Choi
Hanyang University
Naghmeh Karimi
University of Maryland Baltimore County
DescriptionThis session examines how such systems can fail through hardware faults, adversarial manipulation, side channels, and even architectural bugs, and explores mechanisms to restore trust.
Event Type
Research Manuscript
TimeWednesday, July 291:30pm - 3:00pm PDT
LocationMtg Room 202AB
Topics
Security
Tracks
SEC1. AI/ML Security/Privacy
Similar Sessions
RM Poster Session Eight
RM Poster Session Four
RM Poster Session Three
Presentations
1:30pm - 1:42pm PDTAttestllm: Efficient Attestation Framework for Billion-Scale On-Device LLMs
Authors
Ruisi Zhang
Yifei Zhao
Neusha Javidnia
Mengxin Zheng
Farinaz Koushanfar
1:42pm - 1:55pm PDTTargeted Bit-Flip Attacks on LLM-Based Agents
Authors
Jialai Wang
Wen Ya
liu zhongmou
Yuxiao Wu
Bingyi He
Zongpeng Li
Ee-Chien Chang
1:55pm - 2:08pm PDTGPU-Fuzz: Finding Memory Errors in Deep Learning Frameworks
Authors
Zihao Li
Hongyi Lu
Yanan Guo
Zhenkai Zhang
Shuai Wang
Fengwei Zhang
2:08pm - 2:21pm PDTSTRAP-ViT: Segregated Tokens with Randomized - Transformations for Defense Against Adversarial Patches in ViTs
Authors
Nandish Chattopadhyay
Anadi Goyal
Chandan Karfa
Anupam Chattopadhyay
2:21pm - 2:34pm PDTCiphershield: Safeguarding DNN Inputs from Ciphertext Side-Channels in TEE
Authors
Hui Feng
Yuntao Liu
Qian Wang
2:34pm - 2:47pm PDTWFH-BFs: Dynamic Defense Against DNN Bit-Flips via a Weight Function Hierarchy
Authors
Jie Xiao
hao ying
Aizhu Liu
jiajun guo
Zhanhui Shi
Jungang Lou
Fuli Wu
2:47pm - 3:00pm PDTRISCSmith: Finding RISC-V CPU Bugs via Rich Instruction Construction and On-the-Fly Differential Analysis
Authors
Xudong Zhang
Yuanliang Chen
Zehong Yu
Zhen Yan
Fuchen Ma
Dalong Shi
Yu Jiang