Papers by Zhenhao Zhou
Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Kernel Faults (2026.acl-long)
Copied to clipboard
| Challenge: | Existing LLM agents struggle with identifying bugs in the Linux kernel . bugs can affect billions of users, affecting the Linux Foundation's research on the topic . |
| Approach: | They propose a LinuxFLBench benchmark to measure the accuracy of LLM agents on the Linux kernel. |
| Outcome: | The proposed framework improves FL accuracy with minimal costs. |
DiffuseDef: Improved Robustness to Adversarial Attacks via Iterative Denoising (2025.acl-long)
Copied to clipboard
| Challenge: | Existing adversarial defense methods for natural language processing still pose challenges to adversarials. |
| Approach: | They propose a novel adversarial defense method that incorporates a diffusion layer as a denoiser between the encoder and the classifier. |
| Outcome: | The proposed method improves over existing adversarial defense methods and achieves state-of-the-art performance against black-box and white-box adversarials. |
How Adversarial Environments Mislead Agentic AI? (2026.findings-acl)
Copied to clipboard
| Challenge: | Current evaluations benchmark capability in benign settings, but never "what if the tools lie" we formalize this vulnerability as Adversarial Environmental Injection (AEI) AEI constitutes environmental deception by constructing a "fake world" of poisoned search results . |
| Approach: | They propose an attack model where adversaries compromise tool outputs to deceive agents. |
| Outcome: | The proposed model exploits a trust gap between tool outputs and actual exposure to adversaries. |
SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios (2026.acl-long)
Copied to clipboard
Junkai Chen, Huihui Huang, Yunbo Lyu, Junwen An, Jieke Shi, Chengran Yang, Ting Zhang, Haoye Tian, Yikun Li, Zhenhao Li, Xin Zhou, Xing Hu, David Lo
| Challenge: | Existing benchmarks fail to capture scenarios in which vulnerabilities are introduced by humans . we evaluate 5 popular code agents supported by 5 LLMs on SecureVibeBench . |
| Approach: | They propose a benchmarking tool that compares 105 C/C++ secure coding tasks . they use real-world open-source vulnerabilities and a comprehensive evaluation tool . |
| Outcome: | The proposed benchmarks show that code agents struggle to produce correct and secure code . the best performing agent produces merely 23.8% correct and secured solutions . |