Boheng Li
7 papers · 2023–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (5) π Cross-Pollinator (5)
π
Renaissance Researcher
(5)
πΊοΈ
Taxonomy Completionist
(22)
β
The Questioner
Conferences
AAAI (2)
CVPR (2)
ICCV (1)
ICML (1)
NIPS (1)
Top co-authors
Research topics
Keywords
backdoor attack
(2)
deepfake detection
(2)
transfer learning
(1)
anomaly detection
(1)
video synthesis
(1)
self-supervised learning
(1)
multimodal learning
(1)
image synthesis
(1)
machine learning security
(1)
adversarial attack
(1)
adversarial defense
(1)
adversarial perturbation
(1)
generative adversarial network
(1)
evasion attack
(1)
frequency domain
(1)
ownership verification
(1)
image transformation
(1)
audio-visual synchronization
(1)
lip-syncing fraud
(1)
temporal inconsistency
(1)
Papers
Transfer Learning of Real Image Features with Soft Contrastive Loss for Fake Image Detection
AAAI 2025
Invisible Backdoor Attack against Self-supervised Learning
CVPR 2025
Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes
NIPS 2024
Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks
CVPR 2024
TraceEvader: Making DeepFakes More Untraceable via Evading the Forgery Model Attribution
AAAI 2024
Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation
ICML 2024
What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networks
ICCV 2023