Search Results for author:
Found 43 papers, 12 papers with code
On the Effect of Isotropy on VAE Representations of Text
Injecting desired geometric properties into text representations has attracted a lot of attention.
Safety Layers of Aligned Large Language Models: The Key to LLM Security
Aligned LLMs are highly secure, capable of recognizing and refusing to answer malicious questions.
Hide Your Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Neural Carrier Articles
By inserting the malicious query to the carrier article, the assembled attack payload can successfully jailbreak LLM.
S-RAN: Semantic-Aware Radio Access Networks
Semantic communication (SemCom) has been a transformative paradigm, emphasizing the precise exchange of meaningful information over traditional bit-level transmissions.
CTS: A Consistency-Based Medical Image Segmentation Model
Compared to diffusion models, consistency models can reduce the sampling times to once, not only achieving similar generative effects but also significantly speeding up training and prediction.
BadFusion: 2D-Oriented Backdoor Attacks against 3D Object Detection
To tackle this issue, we propose an innovative 2D-oriented backdoor attack against LiDAR-camera fusion methods for 3D object detection, named BadFusion, for preserving trigger effectiveness throughout the entire fusion process.
Micro-Macro Spatial-Temporal Graph-based Encoder-Decoder for Map-Constrained Trajectory Recovery
Recovering intermediate missing GPS points in a sparse trajectory, while adhering to the constraints of the road network, could offer deep insights into users' moving behaviors in intelligent transportation systems.
Double-I Watermark: Protecting Model Copyright for LLM Fine-tuning
To support various applications, a prevalent and efficient approach for business owners is leveraging their valuable datasets to fine-tune a pre-trained LLM through the API provided by LLM owners or cloud servers.
Secure Transformer Inference Protocol
Security of model parameters and user data is critical for Transformer-based services, such as ChatGPT.
Multi-Operational Mathematical Derivations in Latent Space
To this end, we introduce different multi-operational representation paradigms, modelling mathematical operations as explicit geometric transformations.
A Wireless AI-Generated Content (AIGC) Provisioning Framework Empowered by Semantic Communication
Generative AI applications have been recently catering to a vast user base by creating diverse and high-quality AI-generated content (AIGC).
PacketGame: Multi-Stream Packet Gating for Concurrent Video Inference at Scale
The resource efficiency of video analytics workloads is critical for large-scale deployments on edge nodes and cloud clusters.
How Does Naming Affect LLMs on Code Analysis Tasks?
However, one significant difference between programming languages and natural languages is that a programmer has the flexibility to assign any names to variables, methods, and functions in the program, whereas a natural language writer does not.
Ranked #3 on
Code Generation
on MBPP
PATROL: Privacy-Oriented Pruning for Collaborative Inference Against Model Inversion Attacks
Collaborative inference has been a promising solution to enable resource-constrained edge devices to perform inference using state-of-the-art deep neural networks (DNNs).
Fed-CPrompt: Contrastive Prompt for Rehearsal-Free Federated Continual Learning
Federated continual learning (FCL) learns incremental tasks over time from confidential datasets distributed across clients.
Tight Memory-Regret Lower Bounds for Streaming Bandits
We establish the tight worst-case regret lower bound of $\Omega \left( (TB)^{\alpha} K^{1-\alpha}\right), \alpha = 2^{B} / (2^{B+1}-1)$ for any algorithm with a time horizon $T$, number of arms $K$, and number of passes $B$.
FedSDG-FS: Efficient and Secure Feature Selection for Vertical Federated Learning
Vertical Federated Learning (VFL) enables multiple data owners, each holding a different subset of features about largely overlapping sets of data sample(s), to jointly train a useful global model.
Which Features are Learned by CodeBert: An Empirical Study of the BERT-based Source Code Representation Learning
The Bidirectional Encoder Representations from Transformers (BERT) were proposed in the natural language process (NLP) and shows promising results.
Workie-Talkie: Accelerating Federated Learning by Overlapping Computing and Communications via Contrastive Regularization
However, practical deployment of FL over mobile devices is very challenging because (i) conventional FL incurs huge training latency for mobile devices due to interleaved local computing and communications of model updates, (ii) there are heterogeneous training data across mobile devices, and (iii) mobile devices have hardware heterogeneity in terms of computing and communication capabilities.
Distributed Pruning Towards Tiny Neural Networks in Federated Learning
To address these challenges, we propose FedTiny, a distributed pruning framework for federated learning that generates specialized tiny models for memory- and computing-constrained devices.
InFi: End-to-End Learning to Filter Input for Resource-Efficiency in Mobile-Centric Inference
Previous efforts have tailored effective solutions for many applications, but left two essential questions unanswered: (1) theoretical filterability of an inference workload to guide the application of input filtering techniques, thereby avoiding the trial-and-error cost for resource-constrained mobile applications; (2) robust discriminability of feature embedding to allow input filtering to be widely effective for diverse inference tasks and input content.
MLink: Linking Black-Box Models from Multiple Domains for Collaborative Inference
The cost efficiency of model inference is critical to real-world machine learning (ML) applications, especially for delay-sensitive tasks and resource-limited devices.
Federated Semi-Supervised Domain Adaptation via Knowledge Transfer
Further, the proposed FSSDA can be effectively generalized to multi-source domain adaptation scenarios.
Towards Robust On-Ramp Merging via Augmented Multimodal Reinforcement Learning
Moreover, to improve data efficiency and provide better generalization performance, we train the policy model with augmented data (e. g., noisy BSM and noisy surveillance images).
Topology-aware Generalization of Decentralized SGD
Our theory indicates that the generalizability of D-SGD is positively correlated with the spectral gap, and can explain why consensus control in initial training phase can ensure better generalization.
Residue-based Label Protection Mechanisms in Vertical Logistic Regression
To deal with this, we then propose three protection mechanisms, e. g., additive noise mechanism, multiplicative noise mechanism, and hybrid mechanism which leverages local differential privacy and homomorphic encryption techniques, to prevent the attack and improve the robustness of the vertical logistic regression.
Pay "Attention" to Adverse Weather: Weather-aware Attention-based Object Detection
Specifically, GLA integrates an early-stage fusion via a local attention network and a late-stage fusion via a global attention network to deal with both local and global information, which automatically allocates higher weights to the modality with better detection features at the late-stage fusion to cope with the specific weather condition adaptively.
Membership Inference Attacks and Defenses in Neural Network Pruning
We first explore the impact of neural network pruning on prediction divergence, where the pruning process disproportionately affects the pruned model's behavior for members and non-members.
The Neglected Sibling: Isotropic Gaussian Posterior for VAE
Deep generative models have been widely used in several areas of NLP, and various techniques have been proposed to augment them or address their training challenges.
FedZKT: Zero-Shot Knowledge Transfer towards Resource-Constrained Federated Learning with Heterogeneous On-Device Models
To achieve knowledge transfer across these heterogeneous on-device models, a zero-shot distillation approach is designed without any prerequisites for private on-device data, which is contrary to certain prior research based on a public dataset or a pre-trained data generator.
Adaptive perturbation adversarial training: based on reinforcement learning
Adversarial training has become the primary method to defend against adversarial samples.
A Vertical Federated Learning Framework for Horizontally Partitioned Labels
To address these challenges, we propose a novel vertical federated learning framework named Cascade Vertical Federated Learning (CVFL) to fully utilize all horizontally partitioned labels to train neural networks with privacy-preservation.
Unsupervised Representation Disentanglement of Text: An Evaluation on Synthetic Datasets
To highlight the challenges of achieving representation disentanglement for text domain in an unsupervised setting, in this paper we select a representative set of successfully applied models from the image domain.
Age-Stratified COVID-19 Spread Analysis and Vaccination: A Multitype Random Network Approach
As a result, age-stratified modeling for COVID-19 dynamics is the key to study how to reduce hospitalizations and mortality from COVID-19.
Exploring the Galactic Anticenter substructure with LAMOST & Gaia DR2
Their location in [$\alpha$/M] vs. [M/H] space is more metal poor than typical thin disk stars, with [$\alpha$/M] \textbf{lower} than the thick disk.
Astrophysics of Galaxies
ES Attack: Model Stealing against Deep Neural Networks without Data Hurdles
The experimental results reveal the severity of ES Attack: i) ES Attack successfully steals the victim model without data hurdles, and ES Attack even outperforms most existing model stealing attacks using auxiliary data in terms of model accuracy; ii) most countermeasures are ineffective in defending ES Attack; iii) ES Attack facilitates further attacks relying on the stolen model.
Semantic-preserving Reinforcement Learning Attack Against Graph Neural Networks for Malware Detection
As an increasing number of deep-learning-based malware scanners have been proposed, the existing evasion techniques, including code obfuscation and polymorphic malware, are found to be less effective.
Secure Transmission by Leveraging Multiple Intelligent Reflecting Surfaces in MISO Systems
Specifically, to guarantee the worst-case achievable secrecy rate among multiple legitimate users, we formulate a max-min problem that can be solved by an alternative optimization method to decouple it into multiple sub-problems.
A Novel Decision Tree for Depression Recognition in Speech
Depression is a common mental disorder worldwide which causes a range of serious outcomes.
MODMA dataset: a Multi-modal Open Dataset for Mental-disorder Analysis
The EEG dataset includes not only data collected using traditional 128-electrodes mounted elastic cap, but also a novel wearable 3-electrode EEG collector for pervasive applications.
Comprehensive and Efficient Data Labeling via Adaptive Model Scheduling
With limited computing resources and stringent delay, given a data stream and a collection of applicable resource-hungry deep-learning models, we design a novel approach to adaptively schedule a subset of these models to execute on each data item, aiming to maximize the value of the model output (e. g., the number of high-confidence labels).
Using Deep Learning to Solve Computer Security Challenges: A Survey
Although using machine learning techniques to solve computer security challenges is not a new idea, the rapidly emerging Deep Learning technology has recently triggered a substantial amount of interests in the computer security community.
Cryptography and Security
A Resolution Prover for Coalition Logic
We present a prototype tool for automated reasoning for Coalition Logic, a non-normal modal logic that can be used for reasoning about cooperative agency.
