1 citations · 1 across the 8 of their papers we have counts for
5 papers · 1 filter
DICE: Tilting the Odds through Interface Attacks on System One Model
Ben Dong, Tianyi Lu, Zhonghao Guo +1
System One models offer typed judgments that applications can turn into decisions. Their answers, however, are conditional on the state and question supplied by surrounding compone…
AutoUVM: Automated Prefetching Framework for LLMs under UVM Oversubscription
Mao Lin, Hui Feng, Xianzhong Ding +3
Large language models (LLMs) increasingly exceed the memory capacity of commodity GPUs, making memory oversubscription common in practical deployments. NVIDIA Unified Virtual Memor…
The Claws in Plain Sight: Unauthorized Context Disclosure through LLM Agent Tool Calls
Ben Dong, Zhonghao Guo, Tianyi Lu +1
LLM agents routinely construct tool-call arguments from user profiles, conversation history, retrieved documents, and prior tool results. However, legitimate access to contextual i…
Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agents
Ben Dong, Hui Feng, Qian Wang
Modern generative agents such as OpenClaw - an open-source, self-hosted personal assistant with a community skill ecosystem, are gaining attention and are used pervasively. However…
CLOAQ: Combined Logic and Angle Obfuscation for Quantum Circuits
Vincent Langford, Shihan Zhao, Hongyu Zhang +4
In the realm of quantum computing, quantum circuits serve as essential depictions of quantum algorithms, which are then compiled into executable operations for quantum computations…