activity
20222026
most citedUnderstanding Real-world Threats to Deep Learning Models in Android Apps

32 citations · 60 across the 8 of their papers we have counts for

collaborators

9 papers

cs.CL2026

EAVer: Long-Form Factuality Verification as an End-to-End Agentic Policy

Kening Zheng, Aoying Zheng, Zhigang Chang +21

Long-form factuality verification is commonly implemented as a static decompose-search-verify pipeline, with separately prompted modules processing claims and invoking external sea…

cs.CR2026

Beyond Vector Hiding: Breaking and Mitigating Shared-Direction Weight Obfuscation in TEE-Offloaded Large Language Models

Menghui Zhang, Aoying Zheng, Guoxiao Liu +4

Trusted Execution Environment (TEE)-shielded partitioning of Large Language Models (LLMs) accelerates on-device inference by offloading obfuscated linear layers to an untrusted acc…

cs.CR2026

FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks

Aoying Zheng, Anqi Du, Zizhuang Deng +1

Model quantization is essential for the efficient deployment of Large Language Models (LLMs), but introduces a critical vulnerability: Quantization-Conditioned Backdoor (QCB) attac…

cs.CR2026

QuantGuard: Learnable Rounding for Repairing Quantization-Conditioned Backdoors in LLMs

Aoying Zheng, Anqi Du, Zizhuang Deng +3

Model quantization is a key technique for reducing storage and inference costs in large language model deployment. However, recent studies show that the discretization and rounding…

cs.CR2026

PlanGuard: Defending Agents against Indirect Prompt Injection via Planning-based Consistency Verification

Guangyu Gong, Zizhuang Deng

Large Language Model (LLM) agents are increasingly integrated into critical systems, leveraging external tools to interact with the real world. However, this capability exposes the…

cs.CL2025

HLPD: Aligning LLMs to Human Language Preference for Machine-Revised Text Detection

Fangqi Dai, Xingjian Jiang, Zizhuang Deng

To prevent misinformation and social issues arising from trustworthy-looking content generated by LLMs, it is crucial to develop efficient and reliable methods for identifying the…