Shiwen Ou

Shiwen Ou

Auto-generated profile, based on publicly available information

Shiwen Ou

National University of Defense Technology, Hefei, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 October 2025 in IEEE Transactions on Software Engineering
Verified
Journal Article
Open access
SOShiwen Ou
Shiwen Ou
YLYuwei Li
Yuwei Li
LYLu Yu
Lu Yu
CWChengkun Wei
Chengkun Wei
TWTingke Wen
Tingke Wen
ZPZulie Pan
Zulie Pan
Deep learning (DL) frameworks serve as the backbone for a wide range of artificial intelligence applications. However, bugs within DL frameworks can cascade into critical issues in higher-level applications, jeopardizing reliability and security. While numerous techniques have been proposed to detect bugs in DL frameworks, research exploring common API patterns across frameworks and the potential risks they entail remains limited. Notably, many DL frameworks expose similar APIs with overlapping input parameters and functionalities, rendering them vulnerable to shared bugs, where a flaw in one API may extend to analogous APIs in other frameworks. To address this challenge, we propose MirrorFuzz, an automated API fuzzing solution to discover shared bugs in DL frameworks. MirrorFuzz operates in three stages: First, MirrorFuzz collects historical bug data for each API within a DL framework to identify potentially buggy APIs. Second, it matches each buggy API in a specific framework with similar APIs within and across other DL frameworks. Third, it employs large language models (LLMs) to synthesize code for the API under test, leveraging the historical bug data of similar APIs to trigger analogous bugs across APIs. We implement MirrorFuzz and evaluate it on four popular DL frameworks (TensorFlow, PyTorch, OneFlow, and Jittor). Extensive evaluation demonstrates that MirrorFuzz improves code coverage by 39.92% and 98.20% compared to state-of-the-art methods on TensorFlow and PyTorch, respectively. Moreover, MirrorFuzz discovers 315 bugs, 262 of which are newly found, and 80 bugs are fixed, with 52 of these bugs assigned CNVD IDs.

29 April 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
QXQingsong Xie
Qingsong Xie
YLYuwei Li
Yuwei Li
SOShiwen Ou
Shiwen Ou
QCQiangpu Chen
Qiangpu Chen
TWTaiyan Wang
Taiyan Wang
MHMiao Hu
Miao Hu
Mixture-of-experts (MoE) architectures have become the dominant paradigm for scaling open-source large language models, yet their security implications remain insufficiently understood. Recent studies reveal that MoE safety alignment is concentrated in specific ``safety experts'' and ``safety neurons'', but existing methods require modifying model internals, limiting practical applicability. We identify that a small number of critical tokens in harmful prompts disproportionately activate safety experts at specific layers. Motivated by this insight, we propose ClearCut, a prefix-based jailbreak method that exploits this architectural vulnerability through input manipulation alone while remaining mechanistically interpretable. Specifically, ClearCut optimizes a short, semantically natural prefix with a hybrid contrastive-suppression loss that redirects these tokens away from safety experts, bypassing safety alignment without any modification to model weights. Across six mainstream MoE models, ClearCut achieves an average success rate of 64.6\%, outperforming GCG (45.1\%) and AutoDAN (51.2\%), while approaching GateBreaker (61.5\%) which requires model modification. The prefix averages only 5.77 tokens, substantially shorter than existing approaches. By identifying critical tokens and tracking routing changes, ClearCut provides interpretable pathways that reveal how MoE safety mechanisms function. This work exposes a fundamental security risk in MoE architectures, that safety experts can be disproportionately activated and manipulated by a small number of critical tokens. Beyond identifying this vulnerability, we provide ClearCut as a practical tool for security evaluation.

7 October 2026 in Knowledge-Based Systems
Verified
Journal Article
Closed access
QXQingsong Xie
Qingsong Xie
YLYuwei Li
Yuwei Li
SOShiwen Ou
Shiwen Ou
QCQiangpu Chen
Qiangpu Chen
TWTaiyan Wang
Taiyan Wang
MHMiao Hu
Miao Hu