Search Results for author:
Found 23 papers, 11 papers with code
META: Metadata-Empowered Weak Supervision for Text Classification
Based on seed words, we rank and filter motif instances to distill highly label-indicative ones as {``}seed motifs{''}, which provide additional weak supervision.
Prompt-Guided Mask Proposal for Two-Stage Open-Vocabulary Segmentation
To overcome this challenge, existing methods often use multi-modal models like CLIP, which combine image and text features in a shared embedding space to bridge the gap between limited and extensive vocabulary recognition, resulting in a two-stage approach: In the first stage, a mask generator takes an input image to generate mask proposals, and the in the second stage the target mask is picked based on the query.
Text2Layer: Layered Image Generation using Latent Diffusion Model
To achieve layered image generation, we train an autoencoder that is able to reconstruct layered images and train diffusion models on the latent representation.
Patton: Language Model Pretraining on Text-Rich Networks
A real-world text corpus sometimes comprises not only text documents but also semantic links between them (e. g., academic papers in a bibliographic network are linked by citations and co-authorships).
Navigating Alignment for Non-identical Client Class Sets: A Label Name-Anchored Federated Learning Framework
Traditional federated classification methods, even those designed for non-IID clients, assume that each client annotates its local data with respect to the same universal class set.
TwHIN-BERT: A Socially-Enriched Pre-trained Language Model for Multilingual Tweet Representations at Twitter
Most existing PLMs are not tailored to the noisy user-generated text on social media, and the pre-training does not factor in the valuable social engagement logs available in a social network.
OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak Supervision
Most prior works on this matter mine new values for a set of known attributes but cannot handle new attributes that arose from constantly changing data.
SoK: On the Semantic AI Security in Autonomous Driving
In this paper, we perform the first systematization of knowledge of such growing semantic AD AI security research space.
Detecting Multi-Sensor Fusion Errors in Advanced Driver-Assistance Systems
We define the failures (e. g., car crashes) caused by the faulty MSF as fusion errors and develop a novel evolutionary-based domain-specific search framework, FusED, for the efficient detection of fusion errors.
Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks
Specifically, we jointly train two modules with different inductive biases -- a text analysis module for text understanding and a network learning module for class-discriminative, scalable network learning.
i-Algebra: Towards Interactive Interpretability of Deep Neural Networks
Providing explanations for deep neural networks (DNNs) is essential for their use in domains wherein the interpretability of decisions is a critical prerequisite.
Composite Adversarial Training for Multiple Adversarial Perturbations and Beyond
One intriguing property of deep neural networks (DNNs) is their vulnerability to adversarial perturbations.
Trojaning Language Models for Fun and Profit
Recent years have witnessed the emergence of a new paradigm of building natural language processing (NLP) systems: general-purpose, pre-trained language models (LMs) are composed with simple downstream models and fine-tuned for a variety of NLP tasks.
AdvMind: Inferring Adversary Intent of Black-Box Attacks
Deep neural networks (DNNs) are inherently susceptible to adversarial attacks even under black-box settings, in which the adversary only has query access to the target models.
Inf-VAE: A Variational Autoencoder Framework to Integrate Homophily and Influence in Diffusion Prediction
Recent years have witnessed tremendous interest in understanding and predicting information spread on social media platforms such as Twitter, Facebook, etc.
A Tale of Evil Twins: Adversarial Inputs versus Poisoned Models
Specifically, (i) we develop a new attack model that jointly optimizes adversarial inputs and poisoned models; (ii) with both analytical and empirical evidence, we reveal that there exist intriguing "mutual reinforcement" effects between the two attack vectors -- leveraging one vector significantly amplifies the effectiveness of the other; (iii) we demonstrate that such effects enable a large design spectrum for the adversary to enhance the existing attacks that exploit both vectors (e. g., backdoor attacks), such as maximizing the attack evasiveness with respect to various detection methods; (iv) finally, we discuss potential countermeasures against such optimized attacks and their technical challenges, pointing to several promising research directions.
Provable Defenses against Spatially Transformed Adversarial Inputs: Impossibility and Possibility Results
On the possibility side, we show that it is still feasible to construct adversarial training methods to significantly improve the resilience of networks against adversarial inputs over empirical datasets.
Interpretable Deep Learning under Fire
The improved interpretability is believed to offer a sense of security by involving human in the decision-making process.
Model-Reuse Attacks on Deep Learning Systems
By empirically studying four deep learning systems (including both individual and ensemble systems) used in skin cancer screening, speech recognition, face verification, and autonomous steering, we show that such attacks are (i) effective - the host systems misbehave on the targeted inputs as desired by the adversary with high probability, (ii) evasive - the malicious models function indistinguishably from their benign counterparts on non-targeted inputs, (iii) elastic - the malicious models remain effective regardless of various system design choices and tuning strategies, and (iv) easy - the adversary needs little prior knowledge about the data used for system tuning or inference.
Cryptography and Security
EagleEye: Attack-Agnostic Defense against Adversarial Inputs (Technical Report)
Deep neural networks (DNNs) are inherently vulnerable to adversarial inputs: such maliciously crafted samples trigger DNNs to misbehave, leading to detrimental consequences for DNN-powered systems.
Differentially Private Releasing via Deep Generative Model (Technical Report)
Privacy-preserving releasing of complex data (e. g., image, text, audio) represents a long-standing challenge for the data mining research community.
Motif-based Convolutional Neural Network on Graphs
This paper introduces a generalization of Convolutional Neural Networks (CNNs) to graphs with irregular linkage structures, especially heterogeneous graphs with typed nodes and schemas.
Modular Learning Component Attacks: Today's Reality, Tomorrow's Challenge
Many of today's machine learning (ML) systems are not built from scratch, but are compositions of an array of {\em modular learning components} (MLCs).
