ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Boheng Li

Boheng Li

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 5:10 AM AMS

7

papers

57

total citations

papers (7)

Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks

What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networks

Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning

NEURIPS 2025arXiv

Transfer Learning of Real Image Features with Soft Contrastive Loss for Fake Image Detection

Invisible Backdoor Attack against Self-supervised Learning

Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation

TraceEvader: Making DeepFakes More Untraceable via Evading the Forgery Model Attribution