LZ
Leo Zhang
cs.CRcs.AIcs.LGcs.CVcs.DCstat.MLAlgorithmscs.CLcs.CYcs.IT
On Valency
published · living versionsW_9j87nudb·v1 · currentpublished
Silent and Costly: Characterizing and Detecting Prompt-Caching Mis-Integration in LLM Agents
with Ying Zhang, Ruoqi Guo, Yi Liu, Gelei Deng +2
1 version
Preprints & journals
86 papers in the corpus · 2012–2026Rethinking Federated Unlearning via the Lens of Memorization2605.24545v1 · Jiaheng Wei, Yanjun Zhang, He Zhang et al.2026 · 1 citationarXiv
Memory-Guided Unified Hardware Accelerator for Mixed-Precision Scientific Computing2601.04476v1 · Chuanzhen Wang, Leo Zhang, Eric Liu2026 · 0 citationsarXiv
FLAME: Flexible and Lightweight Biometric Authentication Scheme in Malicious Environments2511.02176v1 · Fuyi Wang, Fangyuan Sun, Mingyuan Fan et al.2025 · 0 citationsarXiv
PrivGNN: High-Performance Secure Inference for Cryptographic Graph Neural Networks2511.02185v1 · Fuyi Wang, Zekai Chen, Mingyuan Fan et al.2025 · 0 citationsarXiv
TED++: Submanifold-Aware Backdoor Detection via Layerwise Tubular-Neighbourhood Screening2510.14299v1 · Nam Le, Leo Yu Zhang, Kewen Liao et al.2025 · 0 citationsarXiv
SegTrans: Transferable Adversarial Examples for Segmentation Models2510.08922v1 · Yufei Song, Ziqi Zhou, Qi Lu et al.2025 · 4 citationsarXiv
Towards Real-World Deepfake Detection: A Diverse In-the-wild Dataset of Forgery Faces2510.08067v1 · Junyu Shi, Minghui Li, Junguo Zuo et al.2025 · 0 citationsarXiv
DarkHash: A Data-Free Backdoor Attack Against Deep Hashing2510.08094v1 · Ziqi Zhou, Menghao Deng, Yufei Song et al.2025 · 2 citationsarXiv
CREPE: Controlling Diffusion with Replica Exchange2509.23265v2 · Jiajun He, Paul Jeha, Peter Potaptchik et al.2025 · 0 citationsarXiv
Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and Alignment2509.18717v1 · Tong Zhang, Kuofeng Gao, Jiawang Bai et al.2025 · 0 citationsarXiv
MARS: A Malignity-Aware Backdoor Defense in Federated Learning2509.20383v1 · Wei Wan, Yuxuan Ning, Zhicong Huang et al.2025 · 1 citationarXiv
ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents2509.16645v1 · Yichen Wang, Hangtao Zhang, Hewen Pan et al.2025 · 0 citationsarXiv
Backdoor Attacks and Defenses in Computer Vision Domain: A Survey2509.07504v1 · Bilal Hussain Abbasi, Yanjun Zhang, Leo Zhang et al.2025 · 0 citationsarXiv
BiMark: Unbiased Multilayer Watermarking for Large Language Models2506.21602v2 · Xiaoyan Feng, He Zhang, Yanjun Zhang et al.2025 · 0 citationsarXiv
Towards Reliable Forgetting: A Survey on Machine Unlearning Verification2506.15115v3 · Lulu Xue, Shengshan Hu, Wei Lu et al.2025 · 6 citationsarXiv
TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks2506.10722v1 · Xiaoxing Mo, Yuxuan Cheng, Nan Sun et al.2025 · 0 citationsarXiv
When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive Learning2506.05743v1 · Ruining Sun, Hongsheng Hu, Wei Luo et al.2025 · 0 citationsarXiv
Uncertainty-Aware Metabolic Stability Prediction with Dual-View Contrastive Learning2506.00936v1 · Peijin Guo, Minghui Li, Hewen Pan et al.2025 · 1 citationarXiv
Performance Guaranteed Poisoning Attacks in Federated Learning: A Sliding Mode Approach2505.16403v2 · Huazi Pan, Yanjun Zhang, Leo Yu Zhang et al.2025 · 0 citationsarXiv
MVSF-AB: accurate antibody-antigen binding affinity prediction via multi-view sequence feature learning.39363630 · Li, Minghui, Shi, Yao, Hu, Shengqing et al.2025 · 16 citationsBioinformatics (Oxford, England). 2025;41(5)
Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets2504.11990v1 · Yechao Zhang, Yuxuan Zhou, Tianyu Li et al.2025 · 0 citationsarXiv
Exploring Gradient-Guided Masked Language Model to Detect Textual Adversarial Attacks2504.08798v1 · Xiaomei Zhang, Zhaoxi Zhang, Yanjun Zhang et al.2025 · 0 citationsarXiv
Test-Time Backdoor Detection for Object Detection Models2503.15293v2 · Hangtao Zhang, Yichen Wang, Shihui Yan et al.2025 · 9 citationsarXiv
Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization2503.12793v3 · Yechao Zhang, Yingzhe Xu, Junyu Shi et al.2025 · 6 citationsarXiv
Not All Edges are Equally Robust: Evaluating the Robustness of Ranking-Based Federated Learning2503.08976v3 · Zirui Gong, Yanjun Zhang, Leo Yu Zhang et al.2025 · 2 citationsarXiv
Accelerated Parallel Tempering via Neural Transports2502.10328v4 · Leo Zhang, Peter Potaptchik, Jiajun He et al.2025 · 0 citationsarXiv
Data-Free Model-Related Attacks: Unleashing the Potential of Generative AI2501.16671v1 · Dayong Ye, Tianqing Zhu, Shang Wang et al.2025 · 0 citationsUSENIX Security Symposium 2025
NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors2412.16955v1 · Ziqi Zhou, Bowen Li, Yufei Song et al.2024 · 6 citationsarXiv
PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentation2412.16651v2 · Yufei Song, Ziqi Zhou, Minghui Li et al.2024 · 0 citationsarXiv
FLARE: Toward Universal Dataset Purification against Backdoor Attacks2411.19479v3 · Linshan Hou, Wei Luo, Zhongyun Hua et al.2024 · 9 citationsarXiv
Robot Collapse: Supply Chain Backdoor Attacks Against VLM-based Robotic Manipulation2411.11683v7 · Xianlong Wang, Hewen Pan, Hangtao Zhang et al.2024 · 0 citationsarXiv
SymDiff: Equivariant Diffusion via Stochastic Symmetrisation2410.06262v2 · Leo Zhang, Kianoosh Ashouritaklimi, Yee Whye Teh et al.2024 · 0 citationsarXiv
ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification2406.15093v2 · Xianlong Wang, Shengshan Hu, Yechao Zhang et al.2024 · 1 citationarXiv
Memorization in deep learning: A survey2406.03880v1 · Jiaheng Wei, Yanjun Zhang, Leo Yu Zhang et al.2024 · 16 citationsarXiv
Large Language Model Watermark Stealing With Mixed Integer Programming2405.19677v1 · Zhaoxi Zhang, Xiaomei Zhang, Yanjun Zhang et al.2024 · 1 citationarXiv
Metric Flow Matching for Smooth Interpolations on the Data Manifold2405.14780v2 · Kacper Kapu'sniak, Peter Potaptchik, Teodora Reu et al.2024 · 6 citationsarXiv
IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency2405.09786v3 · Linshan Hou, Ruili Feng, Zhongyun Hua et al.2024 · 10 citationsarXiv
DarkFed: A Data-Free Backdoor Attack in Federated Learning2405.03299v1 · Minghui Li, Wei Wan, Yuxuan Ning et al.2024 · 8 citationsarXiv
Algorithmic Fairness: A Tolerance Perspective2405.09543v1 · Renqiang Luo, Tao Tang, Feng Xia et al.2024 · 1 citationarXiv
Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving2404.11357v2 · Hangtao Zhang, Shengshan Hu, Yichen Wang et al.2024 · 0 citationsarXiv
Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples2403.10801v2 · Ziqi Zhou, Minghui Li, Wei Liu et al.2024 · 11 citationsarXiv
Towards Model Extraction Attacks in GAN-Based Image Translation via Domain Shift Mitigation2403.07673v4 · Di Mi, Yanjun Zhang, Leo Yu Zhang et al.2024 · 6 citationsarXiv
Fluent: Round-efficient Secure Aggregation for Private Federated Learning2403.06143v1 · Xincheng Li, Jianting Ning, Geong Sen Poh et al.2024 · 3 citationsarXiv
Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks2401.16687v1 · Lulu Xue, Shengshan Hu, Ruizhi Zhao et al.2024 · 10 citationsarXiv
MISA: Unveiling the Vulnerabilities in Split Federated Learning2312.11026v2 · Wei Wan, Yuxuan Ning, Shengshan Hu et al.2023 · 6 citationsarXiv
Robust Backdoor Detection for Deep Learning via Topological Evolution Dynamics2312.02673v1 · Xiaoxing Mo, Yechao Zhang, Leo Yu Zhang et al.2023 · 32 citationsarXiv
Detecting and Corrupting Convolution-based Unlearnable Examples2311.18403v3 · Minghui Li, Xianlong Wang, Zhifei Yu et al.2023 · 2 citationsarXiv
AGRAMPLIFIER: Defending Federated Learning Against Poisoning Attacks Through Local Update Amplification2311.06996v2 · Zirui Gong, Liyue Shen, Yanjun Zhang et al.2023 · 30 citationsarXiv
Turn Passive to Active: A Survey on Active Intellectual Property Protection of Deep Learning Models2310.09822v1 · Mingfu Xue, Leo Yu Zhang, Yushu Zhang et al.2023 · 2 citationsarXiv
Client-side Gradient Inversion Against Federated Learning from Poisoning2309.07415v1 · Jiaheng Wei, Yanjun Zhang, Leo Yu Zhang et al.2023 · 5 citationsarXiv
Career total: at least 323 works. 86 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.