Search Results for author:
Found 19 papers, 9 papers with code
Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm?
By analyzing the linkage between membership inference vulnerability and data importance, we demonstrate that sample characteristics can be integrated into membership metrics by introducing sample-specific criteria, therefore enhancing the membership inference performance.
Membership Inference Attacks Against In-Context Learning
Adapting Large Language Models (LLMs) to specific tasks introduces concerns about computational efficiency, prompting an exploration of efficient methods such as In-Context Learning (ICL).
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
To study this problem, we organized a capture-the-flag competition at IEEE SaTML 2024, where the flag is a secret string in the LLM system prompt.
CMT: Cross Modulation Transformer with Hybrid Loss for Pansharpening
In response, we present the Cross Modulation Transformer (CMT), a pioneering method that modifies the attention mechanism.
Instruction Backdoor Attacks Against Customized LLMs
The increasing demand for customized Large Language Models (LLMs) has led to the development of solutions like GPTs.
Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models
Several membership inference attacks (MIAs) have been proposed to exhibit the privacy vulnerability of generative models by classifying a query image as a training dataset member or nonmember.
Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning
Large Language Models (LLMs) are powerful tools for natural language processing, enabling novel applications and user experiences.
Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networks
To fill the gap, we propose a Spiking-Diffusion model, which is based on the vector quantized discrete diffusion model.
Ranked #1 on
Image Generation
on EMNIST-Letters
PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple Extraction
Joint extraction of entities and relations from unstructured texts is a crucial task in information extraction.
Lifelong Learning based Disease Diagnosis on Clinical Notes
Current deep learning based disease diagnosis systems usually fall short in catastrophic forgetting, i. e., directly fine-tuning the disease diagnosis model on new tasks usually leads to abrupt decay of performance on previous tasks.
Node-Level Membership Inference Attacks Against Graph Neural Networks
To fully utilize the information contained in graph data, a new family of machine learning (ML) models, namely graph neural networks (GNNs), has been introduced.
ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models
As a result, we lack a comprehensive picture of the risks caused by the attacks, e. g., the different scenarios they can be applied to, the common factors that influence their performance, the relationship among them, or the effectiveness of possible defenses.
Critical behaviors of the $O(4)$ and $Z(2)$ symmetries in the QCD phase diagram
Various critical exponents related to the order parameter, chiral susceptibilities and correlation lengths have been calculated for the 3-$d$ $O(4)$ and $Z(2)$ universality classes in the phase diagram, respectively.
High Energy Physics - Phenomenology
Dynamic Backdoor Attacks Against Deep Neural Networks
In particular, BaN and c-BaN based on a novel generative network are the first two schemes that algorithmically generate triggers.
Finding Influential Instances for Distantly Supervised Relation Extraction
Distant supervision (DS) is a strong way to expand the datasets for enhancing relation extraction (RE) models but often suffers from high label noise.
Online Disease Self-diagnosis with Inductive Heterogeneous Graph Convolutional Networks
We propose a Healthcare Graph Convolutional Network (HealGCN) to offer disease self-diagnosis service for online users based on Electronic Healthcare Records (EHRs).
Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback
Counterfactual learning for dealing with missing-not-at-random data (MNAR) is an intriguing topic in the recommendation literature since MNAR data are ubiquitous in modern recommender systems.
Dynamic Backdoor Attacks Against Machine Learning Models
Triggers generated by our techniques can have random patterns and locations, which reduce the efficacy of the current backdoor detection mechanisms.
On the Fairness of Randomized Trials for Recommendation with Heterogeneous Demographics and Beyond
Observed events in recommendation are consequence of the decisions made by a policy, thus they are usually selectively labeled, namely the data are Missing Not At Random (MNAR), which often causes large bias to the estimate of true outcomes risk.
