Showing cs.CRShow all
3 papers · 1 filter
cs.CR2026
OptiLeak: Efficient Prompt Reconstruction via Reinforcement Learning in Multi-tenant LLM Services
Longxiang Wang, Xiang Zheng, Xuhao Zhang +3
Multi-tenant LLM serving frameworks widely adopt shared Key-Value caches to enhance efficiency. However, this creates side-channel vulnerabilities enabling prompt leakage attacks.…
cs.CR2026
Rethinking Latency Denial-of-Service: Attacking the LLM Serving Framework, Not the Model
Tianyi Wang, Huawei Fan, Yuanchao Shu +2
Large Language Models face an emerging and critical threat known as latency attacks. Because LLM inference is inherently expensive, even modest slowdowns can translate into substan…
cs.CR2025
HORAM: A High-Performance Hierarchical Doubly Oblivious RAM
Leqian Zheng, Zheng Zhang, Wentao Dong +3
The combination of Oblivious RAM (ORAM) with Trusted Execution Environments (TEE) has found numerous real-world applications due to their complementary nature. TEEs alleviate the p…