5 papers
Groundhog Bit-Flip Attack: Seeding Infinite Generation Loops in Mixture-of-Experts LLMs through Bit Flips
Huakang Lin, Tiancheng Zheng, Mingxuan Sun +4
Mixture-of-Experts (MoE) architectures enable scalable and efficient large language models (LLMs) by selectively activating expert sub-networks through a routing mechanism. However…
SLAC: Access-Driven CPU-to-GPU Side-channel Attacks via System-Level Cache on Apple Silicon
Tianhong Xu, Saion K. Roy, Ruyi Ding +2
Modern heterogeneous System-on-Chip designs integrate CPU cores and a GPU that share a last-level cache (LLC) or system-level cache (SLC). This sharing exposes a new cross-domain a…
MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs
Ruyi Ding, Tianhong Xu, Xinyi Shen +2
The transformer architecture has become a cornerstone of modern AI, fueling remarkable progress across applications in natural language processing, computer vision, and multimodal…
EXAM: Exploiting Exclusive System-Level Cache in Apple M-Series SoCs for Enhanced Cache Occupancy Attacks
Tianhong Xu, Aidong Adam Ding, Yunsi Fei
Cache occupancy attacks exploit the shared nature of cache hierarchies to infer a victim's activities by monitoring overall cache usage, unlike access-driven cache attacks that foc…
Graph in the Vault: Protecting Edge GNN Inference with Trusted Execution Environment
Ruyi Ding, Tianhong Xu, Aidong Adam Ding +1
Wide deployment of machine learning models on edge devices has rendered the model intellectual property (IP) and data privacy vulnerable. We propose GNNVault, the first secure Grap…