Search Results for author:
Found 37 papers, 13 papers with code
Course-Correction: Safety Alignment Using Synthetic Preferences
To improve, we propose fine-tuning LLMs with preference learning, emphasizing the preference for timely course-correction.
Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias
The common toxicity and societal bias in contents generated by large language models (LLMs) necessitate strategies to reduce harm.
Masked AutoDecoder is Effective Multi-Task Vision Generalist
Inspired by the success of general-purpose models in NLP, recent studies attempt to unify different vision tasks in the same sequence format and employ autoregressive Transformers for sequence prediction.
CLAP: Learning Transferable Binary Code Representations with Natural Language Supervision
At the core, our approach boosts superior transfer learning capabilities by effectively aligning binary code with their semantics explanations (in natural language), resulting a model able to generate better embeddings for binary code.
Learning to Prompt Segment Anything Models
SAMs work with two types of prompts including spatial prompts (e. g., points) and semantic prompts (e. g., texts), which work together to prompt SAMs to segment anything on downstream datasets.
Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey
Traditional computer vision generally solves each single task independently by a dedicated model with the task instruction implicitly designed in the model architecture, arising two limitations: (1) it leads to task-specific models, which require multiple models for different tasks and restrict the potential synergies from diverse tasks; (2) it leads to a pre-defined and fixed model interface that has limited interactivity and adaptability in following user' task instructions.
The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation
Therefore, in this study, we delve into LLMs' susceptibility to persuasive conversations, particularly on factual questions that they can answer correctly.
Rethinking Adversarial Training with Neural Tangent Kernel
To the best of our knowledge, it is the first work leveraging the observations of kernel dynamics to improve existing AT methods.
SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models
We present SPHINX, a versatile multi-modal large language model (MLLM) with a joint mixing of model weights, tuning tasks, and visual embeddings.
Ranked #2 on
Visual Question Answering
on BenchLMM
(using extra training data)
One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training
We propose a training-assisted bit flip attack, in which the adversary is involved in the training stage to build a high-risk model to release.
Mercury: An Automated Remote Side-channel Attack to Nvidia Deep Learning Accelerator
One big concern about the usage of the accelerators is the confidentiality of the deployed models: model inference execution on the accelerators could leak side-channel information, which enables an adversary to preciously recover the model details.
Omnipotent Adversarial Training in the Wild
We first introduce an oracle into the adversarial training process to help the model learn a correct data-label conditional distribution.
Prompt Ensemble Self-training for Open-Vocabulary Domain Adaptation
Traditional domain adaptation assumes the same vocabulary across source and target domains, which often struggles with limited transfer flexibility and efficiency while handling target domains with different vocabularies.
Computation and Data Efficient Backdoor Attacks
To address such limitations, we propose a novel confidence-based scoring methodology, which can efficiently measure the contribution of each poisoning sample based on the distance posteriors.
Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge Computing
Transforming off-the-shelf deep neural network (DNN) models into dynamic multi-exit architectures can achieve inference and transmission efficiency by fragmenting and distributing a large DNN model in edge computing scenarios (e. g., edge devices and cloud servers).
MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection
In this paper, we introduce the first DETR framework for Monocular DEtection with a depth-guided TRansformer, named MonoDETR.
3D Object Detection From Monocular Images
Autonomous Driving
+4
Watermarking Pre-trained Encoders in Contrastive Learning
It is challenging to migrate existing watermarking techniques from the classification tasks to the contrastive learning scenario, as the owner of the encoder lacks the knowledge of the downstream tasks which will be developed from the encoder in the future.
An Interpretable Federated Learning-based Network Intrusion Detection Framework
Learning-based Network Intrusion Detection Systems (NIDSs) are widely deployed for defending various cyberattacks.
A General Framework for Defending Against Backdoor Attacks via Influence Graph
In this work, we propose a new and general framework to defend against backdoor attacks, inspired by the fact that attack triggers usually follow a \textsc{specific} type of attacking pattern, and therefore, poisoned training examples have greater impacts on each other during training.
Interpreting Deep Learning Models in Natural Language Processing: A Review
Neural network models have achieved state-of-the-art performances in a wide range of natural language processing (NLP) tasks.
Fingerprinting Multi-exit Deep Neural Network Models via Inference Time
Specifically, we design an effective method to generate a set of fingerprint samples to craft the inference process with a unique and robust inference time cost as the evidence for model ownership.
Towards Robust Point Cloud Models with Context-Consistency Network and Adaptive Augmentation
Extensive evaluations indicate the integration of the two techniques provides much more robustness than existing defense solutions for 3D models.
An MRC Framework for Semantic Role Labeling
We formalize predicate disambiguation as multiple-choice machine reading comprehension, where the descriptions of candidate senses of a given predicate are used as options to select the correct sense.
Ranked #1 on
Semantic Role Labeling
on CoNLL 2005
Fingerprinting Image-to-Image Generative Adversarial Networks
Since the production of a commercial GAN requires substantial computational and human resources, the copyright protection of GANs is urgently needed.
DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation
In this paper, we investigate the effectiveness of data augmentation techniques in mitigating backdoor attacks and enhancing DL models' robustness.
FenceBox: A Platform for Defeating Adversarial Examples with Data Augmentation Techniques
With more and more advanced adversarial attack methods have been developed, a quantity of corresponding defense solutions were designed to enhance the robustness of DNN models.
Privacy-preserving Collaborative Learning with Automatic Transformation Search
Comprehensive evaluations demonstrate that the policies discovered by our method can defeat existing reconstruction attacks in collaborative learning, with high efficiency and negligible impact on the model performance.
Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models
In this paper, we propose a novel watermark removal attack from a different perspective.
A Data Augmentation-based Defense Method Against Adversarial Attacks in Neural Networks
Deep Neural Networks (DNNs) in Computer Vision (CV) are well-known to be vulnerable to Adversarial Examples (AEs), namely imperceptible perturbations added maliciously to cause wrong classification results.
BorderDet: Border Feature for Dense Object Detection
In this paper, We propose a simple and efficient operator called Border-Align to extract "border features" from the extreme point of the border to enhance the point feature.
Mitigating Advanced Adversarial Attacks with More Advanced Gradient Obfuscation Techniques
Extensive evaluations indicate that our solutions can effectively mitigate all existing standard and advanced attack techniques, and beat 11 state-of-the-art defense solutions published in top-tier conferences over the past 2 years.
Investigating Image Applications Based on Spatial-Frequency Transform and Deep Learning Techniques
This report is about applications based on spatial-frequency transform and deep learning techniques.
Learning to Augment Expressions for Few-shot Fine-grained Facial Expression Recognition
Considering the phenomenon of uneven data distribution and lack of samples is common in real-world scenarios, we further evaluate several tasks of few-shot expression learning by virtue of our F2ED, which are to recognize the facial expressions given only few training instances.
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
TEST: an End-to-End Network Traffic Examination and Identification Framework Based on Spatio-Temporal Features Extraction
With more encrypted network traffic gets involved in the Internet, how to effectively identify network traffic has become a top priority in the field.
A Fine-Grained Facial Expression Database for End-to-End Multi-Pose Facial Expression Recognition
First, we create a new facial expression dataset of more than 200k images with 119 persons, 4 poses and 54 expressions.
Facial Expression Recognition
Facial Expression Recognition (FER)
+2
Learning Correlation Space for Time Series
We propose an approximation algorithm for efficient correlation search in time series data.
