Search Results for author:
Found 19 papers, 10 papers with code
JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models
The rapid evolution of artificial intelligence (AI) through developments in Large Language Models (LLMs) and Vision-Language Models (VLMs) has brought significant advancements across various technological domains.
Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters
To address this issue, we introduce JAMBench, a harmful behavior benchmark designed to trigger and evaluate moderation guardrails.
Rethinking Self-training for Semi-supervised Landmark Detection: A Selection-free Approach
Pseudo pretraining and shrink regression are two essential components for such a curriculum, where the former is the first task of the curriculum for providing a better model initialization and the latter is further added in the later rounds to directly leverage the pseudo-labels in a coarse-to-fine manner.
Design as Desired: Utilizing Visual Question Answering for Multimodal Pre-training
In this work, we leverage descriptions in medical reports to design multi-granular question-answer pairs associated with different diseases, which assist the framework in pre-training without requiring extra annotations from experts.
GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models
Our system of different roles will leverage this knowledge graph to generate new jailbreaks, which have proved effective in inducing LLMs to generate unethical or guideline-violating responses.
Unsupervised Domain Adaptation for Anatomical Landmark Detection
The framework leverages self-training and domain adversarial learning to address the domain gap during adaptation.
Anatomical Landmark Detection
Unsupervised Domain Adaptation
PromptMRG: Diagnosis-Driven Prompts for Medical Report Generation
To address these challenges, we propose diagnosis-driven prompts for medical report generation (PromptMRG), a novel framework that aims to improve the diagnostic accuracy of MRG with the guidance of diagnosis-aware prompts.
CertPri: Certifiable Prioritization for Deep Neural Networks via Movement Cost in Feature Space
Therefore, it is crucial to identify the misbehavior of DNN-based software and improve DNNs' quality.
Towards Generalizable Diabetic Retinopathy Grading in Unseen Domains
Diabetic Retinopathy (DR) is a common complication of diabetes and a leading cause of blindness worldwide.
TraffNet: Learning Causality of Traffic Generation for What-if Prediction
Real-time what-if traffic prediction is crucial for decision making in intelligent traffic management and control.
AdvCheck: Characterizing Adversarial Examples via Local Gradient Checking
To address the issues, we introduce the concept of local gradient, and reveal that adversarial examples have a quite larger bound of local gradient than the benign ones.
Learning Robust Representation for Joint Grading of Ophthalmic Diseases via Adaptive Curriculum and Feature Disentanglement
However, prior works either grade DR or DME independently, without considering internal correlations between them, or grade them jointly by shared feature representation, yet ignoring potential generalization issues caused by difficult samples and data bias.
RePFormer: Refinement Pyramid Transformer for Robust Facial Landmark Detection
This paper presents a Refinement Pyramid Transformer (RePFormer) for robust facial landmark detection.
Excitement Surfeited Turns to Errors: Deep Learning Testing Framework Based on Excitable Neurons
By maximizing the number of excitable neurons concerning various wrong behaviors of models, DeepSensor can generate testing examples that effectively trigger more errors due to adversarial inputs, polluted data and incomplete training.
Fight Perturbations with Perturbations: Defending Adversarial Attacks via Neuron Influence
In this paper, we consider defense methods from the general effect of adversarial attacks that take on neurons inside the model.
CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing
Extensive experiments on MINST, CIFAR-10, and a-ImageNet datasets and 7 models (LeNet, ResNet, and VGG) demonstrate the superiority of CatchBackdoor over the state-of-the-art methods, in terms of (1) \emph{effective} - it shows better detection performance, especially on stealthy attacks ($\sim$ $\times$ 2 on average); (2) \emph{extensible} - it is robust to trigger size and can conduct detection without benign examples.
When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model
To this end, we first propose a baseline model equipped with one transformer decoder as detection head.
Ranked #5 on
Face Alignment
on COFW
Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild
The proposed model is equipped with a novel detection head based on heatmap regression, which conducts score and offset predictions simultaneously on low-resolution feature maps.
Ranked #4 on
Face Alignment
on COFW
Deep Person Re-Identification with Improved Embedding and Efficient Training
However, to achieve this, existing deep models prefer to adopt image pairs or triplets to form verification loss, which is inefficient and unstable since the number of training pairs or triplets grows rapidly as the number of training data grows.
