Profiles2022-2026
Zhenting Wang
Rutgers University
13Papers
0Last author
28Unique co-authors
6First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers13
- LED: LLM Enhanced Open-Vocabulary Object Detection without Human Curated Data GenerationAuthor 4 of 7CVPR Findings 2026
- Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based AgentsAuthor 5 of 8ICLR 2025
- CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AIAuthor 3 of 6CVPR 2025
- Invisible Backdoor Attack against Self-supervised LearningAuthor 2 of 10CVPR 2025
- Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion ModelsAuthor 4 of 8S&P 2025
- DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion ModelsAuthor 1 of 5ICLR 2024 · 12 citations
- Where Did I Come From? Origin Attribution of AI-Generated ImagesAuthor 1 of 6NeurIPS 2023 · 44 citations
- NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP ModelsAuthor 3 of 5ACL 2023 · 17 citations
- UNICORN: A Unified Backdoor Trigger Inversion FrameworkAuthor 1 of 4ICLR 2023 · 7 citations
- BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial LearningAuthor 1 of 3CVPR 2022 · 92 citations
- Rethinking the Reverse-engineering of Trojan TriggersAuthor 1 of 5NeurIPS 2022 · 75 citations
- Training with More Confidence: Mitigating Injected and Natural Backdoors During TrainingAuthor 1 of 4NeurIPS 2022 · 67 citations
- Complex Backdoor Detection by Symmetric Feature DifferencingAuthor 4 of 6CVPR 2022 · 35 citations
