244 citations · 306 across the 22 of their papers we have counts for
22 papers
Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
Yanbo Wang, Minzheng Wang, Jian Liang +3
While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures. For safety alignment, the core ch…
A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models
Yanbo Wang, Yongcan Yu, Jian Liang +1
The development of Long-CoT reasoning has advanced LLM performance across various tasks, including language understanding, complex problem solving, and code generation. This paradi…
Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models
Yongcan Yu, Yanbo Wang, Ran He +1
While (multimodal) large language models (LLMs) have attracted widespread attention due to their exceptional capabilities, they remain vulnerable to jailbreak attacks. Various defe…
Sample Correlation for Fingerprinting Deep Face Recognition
Jiyang Guan, Jian Liang, Yanbo Wang +1
Face recognition has witnessed remarkable advancements in recent years, thanks to the development of deep learning techniques.However, an off-the-shelf face recognition model as a…
STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay
Yongcan Yu, Lijun Sheng, Ran He +1
Test-time adaptation (TTA) aims to address the distribution shift between the training and test data with only unlabeled data at test time. Existing TTA methods often focus on impr…
Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
Yanbo Wang, Jian Liang, Ran He
Gradient inversion attacks aim to reconstruct local training data from intermediate gradients exposed in the federated learning framework. Despite successful attacks, all previous…
Exploring Vacant Classes in Label-Skewed Federated Learning
Kuangpu Guo, Yuhe Ding, Jian Liang +3
Label skews, characterized by disparities in local label distribution across clients, pose a significant challenge in federated learning. As minority classes suffer from worse accu…
Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization
Jian Liang, Lijun Sheng, Zhengbo Wang +2
The emergence of vision-language models, such as CLIP, has spurred a significant research effort towards their application for downstream supervised learning tasks. Although some p…
Test-Time Backdoor Defense via Detecting and Repairing
Jiyang Guan, Jian Liang, Ran He
Deep neural networks have played a crucial part in many critical domains, such as autonomous driving, face recognition, and medical diagnosis. However, deep neural networks are fac…
Improving Zero-Shot Generalization for CLIP with Synthesized Prompts
Zhengbo Wang, Jian Liang, Ran He +3
With the growing interest in pretrained vision-language models like CLIP, recent research has focused on adapting these models to downstream tasks. Despite achieving promising resu…
Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classification
Yongcan Yu, Lijun Sheng, Ran He +1
Test-time adaptation (TTA) is a technique aimed at enhancing the generalization performance of models by leveraging unlabeled samples solely during prediction. Given the need for r…
TALL: Thumbnail Layout for Deepfake Video Detection
Yuting Xu, Jian Liang, Gengyun Jia +3
The growing threats of deepfakes to society and cybersecurity have raised enormous public concerns, and increasing efforts have been devoted to this critical topic of deepfake vide…
Mind the Label Shift of Augmentation-based Graph OOD Generalization
Junchi Yu, Jian Liang, Ran He
Out-of-distribution (OOD) generalization is an important issue for Graph Neural Networks (GNNs). Recent works employ different graph editions to generate augmented environments and…
MODIFY: Model-driven Face Stylization without Style Images
Yuhe Ding, Jian Liang, Jie Cao +2
Existing face stylization methods always acquire the presence of the target (style) domain during the translation process, which violates privacy regulations and limits their appli…
A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
Jian Liang, Ran He, Tieniu Tan
Machine learning methods strive to acquire a robust model during the training process that can effectively generalize to test samples, even in the presence of distribution shifts.…
AUTO: Adaptive Outlier Optimization for Test-Time OOD Detection
Puning Yang, Jian Liang, Jie Cao +1
Out-of-distribution (OOD) detection aims to detect test samples that do not fall into any training in-distribution (ID) classes. Prior efforts focus on regularizing models with ID…
AdaptGuard: Defending Against Universal Attacks for Model Adaptation
Lijun Sheng, Jian Liang, Ran He +2
Model adaptation aims at solving the domain transfer problem under the constraint of only accessing the pretrained source models. With the increasing considerations of data privacy…
MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection
Yuhe Ding, Jian Liang, Bo Jiang +2
Existing cross-domain keypoint detection methods always require accessing the source data during adaptation, which may violate the data privacy law and pose serious security concer…
Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks
Jiyang Guan, Jian Liang, Ran He
An off-the-shelf model as a commercial service could be stolen by model stealing attacks, posing great threats to the rights of the model owner. Model fingerprinting aims to verify…
ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation
Yuhe Ding, Lijun Sheng, Jian Liang +2
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Owing to privacy concerns and heavy data transmission, s…
UMAD: Universal Model Adaptation under Domain and Category Shift
Jian Liang, Dapeng Hu, Jiashi Feng +1
Learning to reject unknown samples (not present in the source classes) in the target domain is fairly important for unsupervised domain adaptation (UDA). There exist two typical UD…
DINE: Domain Adaptation from Single and Multiple Black-box Predictors
Jian Liang, Dapeng Hu, Jiashi Feng +1
To ease the burden of labeling, unsupervised domain adaptation (UDA) aims to transfer knowledge in previous and related labeled datasets (sources) to a new unlabeled dataset (targe…