Profiles2021-2026
Xuhong Zhang
Zhejiang University
42Papers
10Last author
80Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers42
- HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability DetectorsAuthor 5 of 5AAAI 2026 · 2 citations
- GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient RectificationAuthor 7 of 7ACL Findings 2026 · 1 citation
- Ground What You See: Hallucination-Resistant MLLMs via Caption Feedback, Diversity-Aware Sampling, and Conflict RegularizationAuthor 7 of 7AAAI 2026 · 1 citation
- PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable PromptsAuthor 8 of 8ICML 2026
- RAGFort: Dual-Path Defense Against Proprietary Knowledge Base Extraction in Retrieval-Augmented GenerationAuthor 8 of 8AAAI 2026
- Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only InterventionsAuthor 9 of 9ICML 2026
- Uncovering LLM-Generated Code: A Zero-Shot Synthetic Code Detector via Code RewritingAuthor 5 of 7AAAI 2025 · 21 citations
- MEraser: An Effective Fingerprint Erasure Approach for Large Language ModelsAuthor 5 of 6ACL 2025 · 16 citations
- CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge DeploymentAuthor 3 of 11NeurIPS 2025 · 9 citations
- An Inversion-Based Measure of Memorization for Diffusion ModelsAuthor 3 of 8ICCV 2025 · 5 citations
- DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language ModelsAuthor 13 of 13AAAI 2025 · 4 citations
- Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering TasksAuthor 2 of 7ACL Findings 2025 · 1 citation
- Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual UnderstandingAuthor 9 of 9ICLR 2025
- CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP ModelsAuthor 4 of 6NDSS 2025
- CollabEdit: Towards Non-destructive Collaborative Knowledge EditingAuthor 4 of 6ICLR 2025
- Tool-Planner: Task Planning with Clusters across Multiple ToolsAuthor 6 of 10ICLR 2025
- Exploring ChatGPT's Capabilities on Vulnerability ManagementAuthor 6 of 10USENIX Security 2024 · 52 citations
- RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-FeedbackAuthor 3 of 7ACL Findings 2024 · 35 citations
- ERA-CoT: Improving Chain-of-Thought through Entity Relationship AnalysisAuthor 6 of 6ACL 2024 · 18 citations
- Critical Code Guided Directed Greybox Fuzzing for CommitsAuthor 2 of 8USENIX Security 2024 · 14 citations
- AdaCCD: Adaptive Semantic Contrasts Discovery Based Cross Lingual Adaptation for Code Clone DetectionAuthor 4 of 5AAAI 2024 · 9 citations
- SecCoder: Towards Generalizable and Robust Secure Code GenerationAuthor 4 of 8EMNLP 2024 · 5 citations
- Improving the Robustness of Transformer-based Large Language Models with Dynamic AttentionAuthor 5 of 7NDSS 2024
- MOCK: Optimizing Kernel Fuzzing Mutation with Context-aware DependencyAuthor 2 of 8NDSS 2024
- Efficient Query-Based Attack against ML-Based Android Malware Detection under Zero Knowledge SettingAuthor 3 of 4CCS 2023 · 13 citations
- FreeEagle: Detecting Complex Neural Trojans in Data-Free CasesAuthor 2 of 7USENIX Security 2023
- How IoT Re-using Threatens Your Sensitive Data: Exploring the User-Data Disposal in Used IoT DevicesAuthor 5 of 8S&P 2023
- UVSCAN: Detecting Third-Party Component Usage Violations in IoT FirmwareAuthor 3 of 8USENIX Security 2023
- NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron IdentificationAuthor 4 of 9ICSE 2022 · 58 citations
- A large-scale empirical analysis of the vulnerabilities introduced by third-party components in IoT firmwareAuthor 8 of 11ISSTA 2022 · 49 citations
Showing the 30 most recent indexed papers.
