Profiles2021-2026
Zhibo Wang
Zhejiang University
23Papers
1Last author
61Unique co-authors
6First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers23
- Can Small Language Models Reliably Resist Jailbreak Attacks? A Comprehensive EvaluationAuthor 1 of 6CCS 2026 · 11 citations
- PromptCOS: Towards Content-Only System Prompt Copyright Auditing for LLMsAuthor 7 of 9S&P 2026 · 5 citations
- JailbreakScope: Interpreting Jailbreak Mechanism through Representation and Circuit AnalysesAuthor 2 of 7USENIX Security 2026
- On Evaluating the Robustness of Large Vision-Language Models via Untargeted Modality Alignment Breaking Adversarial AttackAuthor 3 of 8USENIX Security 2026
- ICLScan: Detecting Backdoors in Black-Box Large Language Models via Targeted In-context IlluminationAuthor 5 of 5NeurIPS 2025 · 7 citations
- PoiSAFL: Scalable Poisoning Attack Framework to Byzantine-resilient Semi-asynchronous Federated LearningAuthor 3 of 9USENIX Security 2025
- SoK: On Gradient Leakage in Federated LearningAuthor 3 of 8USENIX Security 2025
- Textual Unlearning Gives a False Sense of UnlearningAuthor 2 of 6ICML 2025
- Byzantine-robust Decentralized Federated Learning via Dual-domain Clustering and Trust BootstrappingAuthor 3 of 4CVPR 2024 · 21 citations
- Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated LearningAuthor 1 of 7INFOCOM 2024 · 10 citations
- FaceObfuscator: Defending Deep Learning-based Privacy Attacks with Gradient Descent-resistant Features in Face RecognitionAuthor 3 of 11USENIX Security 2024 · 9 citations
- A Causal Explainable Guardrails for Large Language ModelsAuthor 4 of 6CCS 2024 · 5 citations
- DAAP: Privacy-Preserving Model Accuracy Estimation on Unlabeled Datasets Through Distribution-Aware Adversarial PerturbationAuthor 2 of 4USENIX Security 2024
- Locate and Verify: A Two-Stream Network for Improved Deepfake DetectionAuthor 5 of 9ACM MM 2023 · 52 citations
- DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery CluesAuthor 7 of 9ACM MM 2023 · 35 citations
- Counterfactual-based Saliency Map: Towards Visual Contrastive Explanations for Neural NetworksAuthor 2 of 8ICCV 2023 · 15 citations
- Towards Fairness-aware Adversarial Network PruningAuthor 2 of 5ICCV 2023 · 8 citations
- Privacy-preserving Adversarial Facial FeaturesAuthor 1 of 10CVPR 2023
- Towards Transferable Targeted Adversarial ExamplesAuthor 1 of 7CVPR 2023
- mmEve: eavesdropping on smartphone's earpiece via COTS mmWave deviceAuthor 5 of 9MobiCom 2022 · 60 citations
- Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep ModelsAuthor 1 of 6CVPR 2022 · 49 citations
- "Adversarial Examples" for Proof-of-LearningAuthor 4 of 6S&P 2022 · 41 citations
- Feature Importance-aware Transferable Adversarial AttacksAuthor 1 of 6ICCV 2021 · 306 citations
