Search Results for author:
Found 86 papers, 44 papers with code
Detecting Annotation Errors in Morphological Data with the Transformer
Annotation errors that stem from various sources are usually unavoidable when performing large-scale annotation of linguistic data.
Backtranslation in Neural Morphological Inflection
Backtranslation is a common technique for leveraging unlabeled data in low-resource scenarios in machine translation.
IGT2P: From Interlinear Glossed Texts to Paradigms
An intermediate step in the linguistic analysis of an under-documented language is to find and organize inflected forms that are attested in natural speech.
Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable
While safety alignment has been extensively studied for LLM, there is still a large research gap for Large Reasoning Models (LRMs) that equip with improved reasoning capability.
Multi-Agent Reinforcement Learning with Focal Diversity Optimization
First, we develop an agent-fusion framework for encouraging multiple LLM based agents to collaborate in producing the final inference output for each LLM query.
Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation
By designing a new red-teaming method, we in this paper show that purely relying on the moderation guardrail for data filtration is not reliable.
From Intention To Implementation: Automating Biomedical Research via LLMs
Conventional biomedical research is increasingly labor-intensive due to the exponential growth of scientific literature and datasets.
$H^3$Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs
The former penalizes the selection errors of the expert-router, and the latter mediates the expert weights drifting during fine-tuning and dynamically adjusts the fusion behavior of the resulting model by canalizing the activations on the experts.
Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models
The safety alignment ability of Vision-Language Models (VLMs) is prone to be degraded by the integration of the vision module compared to its LLM backbone.
LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity
This paper presents LLM-TOPLA, a diversity-optimized LLM ensemble method with three unique properties: (i) We introduce the focal diversity metric to capture the diversity-performance correlation among component LLMs of an ensemble.
Beyond correlation: The Impact of Human Uncertainty in Measuring the Effectiveness of Automatic Evaluation and LLM-as-a-Judge
Specifically, we demonstrate that when the proportion of samples with variation or uncertainty in human assigned labels is relatively high, machine labels (generated by automatic evaluation methods) may superficially appear to have similar or better correlation with the human majority label compared to the human-to-human (HH) correlation.
Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey
To clear up concern, this paper provide a comprehensive overview to three aspects of harmful fine-tuning: attacks setting, defense design and evaluation methodology.
Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
For the first time in the literature, we in this paper show that \textit{harmful perturbation} over the model weights should be the root cause of alignment-broken of harmful fine-tuning.
Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning
To this end, we propose Antidote, a post-fine-tuning stage solution, which remains \textbf{\textit{agnostic to the training hyper-parameters in the fine-tuning stage}}.
Personalized Privacy Protection Mask Against Unauthorized Facial Recognition
Second, we incorporate a perceptibility optimization to preserve the visual quality of the protected facial images.
Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
Recent studies show that Large Language Models (LLMs) with safety alignment can be jail-broken by fine-tuning on a dataset mixed with harmful data.
ConSiDERS-The-Human Evaluation Framework: Rethinking Human Evaluation for Generative Large Language Models
In this position paper, we argue that human evaluation of generative large language models (LLMs) should be a multidisciplinary undertaking that draws upon insights from disciplines such as user experience research and human behavioral psychology to ensure that the experimental design and results are reliable.
Robust Few-Shot Ensemble Learning with Focal Diversity-Based Pruning
This paper presents FusionShot, a focal diversity optimized few-shot ensemble learning approach for boosting the robustness and generalization performance of pre-trained few-shot models.
A Survey on Large Language Model-Based Game Agents
The development of game agents holds a critical role in advancing towards Artificial General Intelligence.
Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
The new paradigm of finetuning-as-a-service introduces a new attack surface for Large Language Models (LLMs): a few harmful data uploaded by users can easily trick the finetuning to produce an alignment-broken model.
PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models
We introduce PokeLLMon, the first LLM-embodied agent that achieves human-parity performance in tactical battle games, as demonstrated in Pokemon battles.
Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance
Emerging Distributed AI systems are revolutionizing big data computing and data processing capabilities with growing economic and societal impact.
TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding
Humans commonly work with multiple objects in daily life and can intuitively transfer manipulation skills to novel objects by understanding object functional regularities.
Resource-Efficient Transformer Pruning for Finetuning of Large Models
With the recent advances in vision transformers and large language models (LLMs) finetuning costly large models on downstream learning tasks poses significant challenges under limited computational resources.
Hierarchical Pruning of Deep Ensembles with Focal Diversity
This paper presents a novel deep ensemble pruning approach, which can efficiently identify smaller deep ensembles and provide higher ensemble accuracy than the entire deep ensemble of a large number of member networks.
Exploring Model Learning Heterogeneity for Boosting Ensemble Robustness
We show that this two-tier heterogeneity driven ensemble construction method can compose an ensemble team that promotes high ensemble diversity and low negative correlation among member models of the ensemble, strengthening ensemble robustness against both negative examples and adversarial attacks.
Large Language Model-Powered Smart Contract Vulnerability Detection: New Perspectives
The goal of auditor is to yield a broad spectrum of vulnerabilities with the hope of encompassing the correct answer, whereas the goal of critic that evaluates the validity of identified vulnerabilities is to minimize the number of false positives.
RAI4IoE: Responsible AI for Enabling the Internet of Energy
This paper plans to develop an Equitable and Responsible AI framework with enabling techniques and algorithms for the Internet of Energy (IoE), in short, RAI4IoE.
Fast and Resource-Efficient Object Tracking on Edge Devices: A Measurement Study
Object tracking is an important functionality of edge video analytic systems and services.
Explicit Time Embedding Based Cascade Attention Network for Information Popularity Prediction
Predicting information cascade popularity is a fundamental problem in social networks.
ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback
This research sheds light on the potential of ChatGPT and conversational LLMs for drug editing.
Demystifying Fraudulent Transactions and Illicit Nodes in the Bitcoin Network for Financial Forensics
This enables both the detection of fraudulent transactions and the detection of illicit addresses (actors) in the Bitcoin network by leveraging four types of graph data: (i) the transaction-to-transaction graph, representing the money flow in the Bitcoin network, (ii) the address-to-address interaction graph, capturing the types of transaction flows between Bitcoin addresses, (iii) the address-transaction graph, representing the bi-directional money flow between addresses and transactions (BTC flow from input address to one or more transactions and BTC flow from a transaction to one or more output addresses), and (iv) the user entity graph, capturing clusters of Bitcoin addresses representing unique Bitcoin users.
Securing Distributed SGD against Gradient Leakage Threats
Next, we present a gradient leakage resilient approach to securing distributed SGD in federated learning, with differential privacy controlled noise as the tool.
BERT4ETH: A Pre-trained Transformer for Ethereum Fraud Detection
As various forms of fraud proliferate on Ethereum, it is imperative to safeguard against these malicious activities to protect susceptible users from being victimized.
STDLens: Model Hijacking-Resilient Federated Learning for Object Detection
Based on the insights, we introduce a three-tier forensic framework to identify and expel Trojaned gradients and reclaim the performance over the course of FL.
Adaptive Deep Neural Network Inference Optimization with EENet
Instead of having every sample go through all DNN layers during prediction, EENet learns an early exit scheduler, which can intelligently terminate the inference earlier for certain predictions, which the model has high confidence of early exit.
ScaleFL: Resource-Adaptive Federated Learning With Heterogeneous Clients
In most FL approaches, all edge clients are assumed to have sufficient computation capabilities to participate in the learning of a deep neural network (DNN) model.
Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing
Here we present a multi-modal molecule structure-text model, MoleculeSTM, by jointly learning molecules' chemical structures and textual descriptions via a contrastive learning strategy.
Automatic Discovery of Multi-perspective Process Model using Reinforcement Learning
Process mining is a methodology for the derivation and analysis of process models based on the event log.
Metric Learning as a Service with Covariance Embedding
With the emergence of deep learning, metric learning has gained significant popularity in numerous machine learning tasks dealing with complex and large-scale datasets, such as information retrieval, object recognition and recommendation systems.
Selecting and Composing Learning Rate Policies for Deep Neural Networks
First, we develop an LR tuning mechanism for auto-verification of a given LR policy with respect to the desired accuracy goal under the pre-defined training time constraint.
Embedded Silicon-Organic Integrated Neuromorphic System
The development of artificial intelligence (AI) and robotics are both based on the tenet of "science and technology are people-oriented", and both need to achieve efficient communication with the human brain.
Gradient Leakage Attack Resilient Deep Learning
Although deep learning with differential privacy is a defacto standard for publishing deep learning models with differential privacy guarantee, we show that differentially private algorithms with fixed privacy parameters are vulnerable against gradient leakage attacks.
Boosting Deep Ensemble Performance with Hierarchical Pruning
Evaluated using two benchmark datasets, we show that the proposed focal diversity powered hierarchical pruning can find significantly smaller ensembles of deep neural network models while achieving the same or better classification generalizability.
Learning Text-Image Joint Embedding for Efficient Cross-Modal Retrieval with Deep Feature Engineering
This paper introduces a two-phase deep feature engineering framework for efficient learning of semantics enhanced joint embedding, which clearly separates the deep feature engineering in data preprocessing from training the text-image joint embedding model.
Network Representation Learning: From Preprocessing, Feature Extraction to Node Embedding
This survey paper reviews the design principles and the different node embedding techniques for network representation learning over homogeneous networks.
Learning Joint Embedding with Modality Alignments for Cross-Modal Retrieval of Recipes and Food Images
This paper presents a three-tier modality alignment approach to learning text-image joint embedding, coined as JEMA, for cross-modal retrieval of cooking recipes and food images.
Learning TFIDF Enhanced Joint Embedding for Recipe-Image Cross-Modal Retrieval Service
We present a Multi-modal Semantics enhanced Joint Embedding approach (MSJE) for learning a common feature space between the two modalities (text and image), with the ultimate goal of providing high-performance cross-modal retrieval services.
Efficient Deep Feature Calibration for Cross-Modal Joint Embedding Learning
This paper introduces a two-phase deep feature calibration framework for efficient learning of semantics enhanced text-image cross-modal joint embedding, which clearly separates the deep feature calibration in data preprocessing from training the joint embedding model.
To POS Tag or Not to POS Tag: The Impact of POS Tags on Morphological Learning in Low-Resource Settings
However, the importance and usefulness of POS tags needs to be examined as NLP expands to low-resource languages because linguists who provide many annotated resources do not place priority on early identification and tagging of POS.
Parallel Detection for Efficient Video Analytics at the Edge
A common performance requirement in these mission-critical edge services is the near real-time latency of online object detection on edge devices.
Gradient-Leakage Resilient Federated Learning
This paper presents a gradient leakage resilient approach to privacy-preserving federated learning with per training example-based client differential privacy, coined as Fed-CDP.
Boosting Ensemble Accuracy by Revisiting Ensemble Diversity Metrics
Our new metrics significantly improve the intrinsic correlation between high ensemble diversity and high ensemble accuracy.
Computational Morphology with Neural Network Approaches
Neural network approaches have been applied to computational morphology with great success, improving the performance of most tasks by a large margin and providing new perspectives for modeling.
De-Pois: An Attack-Agnostic Defense against Data Poisoning Attacks
The results demonstrate that De-Pois is effective and efficient for detecting poisoned data against all the four types of poisoning attacks, with both the accuracy and F1-score over 0. 9 on average.
Can a Transformer Pass the Wug Test? Tuning Copying Bias in Neural Morphological Inflection Models
Deep learning sequence models have been successfully applied to the task of morphological inflection.
Deep Ensembles with Hierarchical Diversity Pruning
(3) We introduce a two phase hierarchical pruning method to effectively identify and prune those deep ensembles with high HQ diversity scores, aiming to increase the lower and upper bounds on ensemble accuracy for the selected ensembles.
Analogy Models for Neural Word Inflection
Analogy is assumed to be the cognitive mechanism speakers resort to in order to inflect an unknown form of a lexeme based on knowledge of other words in a language.
Promoting High Diversity Ensemble Learning with EnsembleBench
Ensemble learning is gaining renewed interests in recent years.
Utility-Optimized Synthesis of Differentially Private Location Traces
Given a real trace dataset D, the differential privacy parameter epsilon controlling the strength of privacy protection, and the utility/error metric Err of interest; OptaTrace uses Bayesian optimization to optimize DPLTS such that the output error (measured in terms of given metric Err) is minimized while epsilon-differential privacy is satisfied.
Robust Deep Learning Ensemble against Deception
Third, XEnsemble provides a suite of algorithms to combine input verification and output verification to protect the DNN prediction models from both adversarial examples and out of distribution inputs.
Data Poisoning Attacks Against Federated Learning Systems
Federated learning (FL) is an emerging paradigm for distributed training of large-scale deep neural networks in which participants' data remains on their own devices with only model updates being shared with a central server.
Bitcoin Transaction Forecasting with Deep Network Representation Learning
First, we explore three interesting properties between Bitcoin transaction accounts: topological connectivity pattern of Bitcoin accounts, transaction amount pattern, and transaction dynamics.
Understanding Object Detection Through An Adversarial Lens
We demonstrate that the proposed framework can serve as a methodical benchmark for analyzing adversarial behaviors and risks in real-time object detection systems.
LDP-Fed: Federated Learning with Local Differential Privacy
However, in federated learning model parameter updates are collected iteratively from each participant and consist of high dimensional, continuous values with high precision (10s of digits after the decimal point), making existing LDP protocols inapplicable.
A Framework for Evaluating Gradient Leakage Attacks in Federated Learning
FL offers default client privacy by allowing clients to keep their sensitive data on local devices and to only share local training parameter updates with the federated server.
TOG: Targeted Adversarial Objectness Gradient Attacks on Real-time Object Detection Systems
The rapid growth of real-time huge data capturing has pushed the deep learning and data analytic computing to the edge systems.
A Two stage Adaptive Knowledge Transfer Evolutionary Multi-tasking Based on Population Distribution for Multi/Many-Objective Optimization
Experimental results on multi-tasking multi-objective optimization test suites show that EMT-PD is superior to other six state-of-the-art evolutionary multi/single-tasking algorithms.
Effects of Differential Privacy and Data Skewness on Membership Inference Vulnerability
Second, through MPLens, we highlight how the vulnerability of pre-trained models under membership inference attack is not uniform across all classes, particularly when the training data itself is skewed.
Cross-Layer Strategic Ensemble Defense Against Adversarial Examples
Deep neural network (DNN) has demonstrated its success in multiple domains.
Deep Neural Network Ensembles against Deception: Ensemble Diversity, Accuracy and Robustness
In this paper we first give an overview of the concept of ensemble diversity and examine the three types of ensemble diversity in the context of DNN classifiers.
Denoising and Verification Cross-Layer Ensemble Against Black-box Adversarial Attacks
Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks.
Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks
Learning Rate (LR) is an important hyper-parameter to tune for effective training of deep neural networks (DNNs).
Secure and Utility-Aware Data Collection with Condensed Local Differential Privacy
In this paper, we address the small user population problem by introducing the concept of Condensed Local Differential Privacy (CLDP) as a specialization of LDP, and develop a suite of CLDP protocols that offer desirable statistical utility while preserving privacy.
Cryptography and Security Databases
Differentially Private Model Publishing for Deep Learning
However, when the training datasets are crowdsourced from individuals and contain sensitive information, the model parameters may encode private information and bear the risks of privacy leakage.
A Comparative Measurement Study of Deep Learning as a Service Framework
Big data powered Deep Learning (DL) and its applications have blossomed in recent years, fueled by three technological trends: a large amount of digitized data openly accessible, a growing number of DL software frameworks in open source and commercial markets, and a selection of affordable parallel computing hardware devices.
A Computational Model for the Linguistic Notion of Morphological Paradigm
In supervised learning of morphological patterns, the strategy of generalizing inflectional tables into more abstract paradigms through alignment of the longest common subsequence found in an inflection table has been proposed as an efficient method to deduce the inflectional behavior of unseen word forms.
Adversarial Examples in Deep Learning: Characterization and Divergence
The burgeoning success of deep learning has raised the security and privacy concerns as more and more tasks are accompanied with sensitive data.
Towards Demystifying Membership Inference Attacks
Our empirical results additionally show that (1) using the type of target model under attack within the attack model may not increase attack effectiveness and (2) collaborative learning in federated systems exposes vulnerabilities to membership inference risks when the adversary is a participant in the federation.
Cryptography and Security
