Search Results for author:
Found 56 papers, 9 papers with code
Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMs
To show the impact of the bias, this paper proposes a Bias Retrieval and Reward Attack (BRRA) framework, which systematically investigates attack pathways that amplify language model biases through a RAG system manipulation.
Recovering Fairness Directly from Modularity: a New Way for Fair Community Partitioning
Community partitioning is crucial in network analysis, with modularity optimization being the prevailing technique.
Chain-of-Lure: A Synthetic Narrative-Driven Approach to Compromise Large Language Models
In the era of rapid generative AI development, interactions between humans and large language models face significant misusing risks.
Do Fairness Interventions Come at the Cost of Privacy: Evaluations for Binary Classifiers
While in-processing fairness approaches show promise in mitigating biased predictions, their potential impact on privacy leakage remains under-explored.
Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearning
For example, the adversary can challenge the model owner by revealing that, despite efforts to unlearn it, the influence of the duplicated subset remains in the model.
Data-Free Model-Related Attacks: Unleashing the Potential of Generative AI
Generative AI technology has become increasingly integrated into our daily lives, offering powerful capabilities to enhance productivity.
AFed: Algorithmic Fair Federated Learning
Federated Learning (FL) has gained significant attention as it facilitates collaborative machine learning among multiple clients without centralizing their data on a server.
Vertical Federated Unlearning via Backdoor Certification
We introduce an innovative modification to traditional VFL by employing a mechanism that inverts the typical learning trajectory with the objective of extracting specific data contributions.
Large Language Models Merging for Enhancing the Link Stealing Attack on Graph Neural Networks
However, we find that an attacker can combine the data knowledge of multiple attackers to create a more effective attack model, which can be referred to cross-dataset attacks.
Machine Unlearning on Pre-trained Models by Residual Feature Alignment Using LoRA
Machine unlearning is new emerged technology that removes a subset of the training data from a trained model without affecting the model performance on the remaining data.
New Emerged Security and Privacy of Pre-trained Model: a Survey and Outlook
With the taxonomy analysis, we capture the unique security and privacy issues of pre-trained models, categorizing and summarizing existing security issues based on their characteristics.
Game-Theoretic Machine Unlearning: Mitigating Extra Privacy Leakage
Additionally, the experimental results on real-world datasets demonstrate that this game-theoretic unlearning algorithm's effectiveness and its ability to generate an unlearned model with a performance similar to that of the retrained one while mitigating extra privacy leakage risks.
Zero-shot Class Unlearning via Layer-wise Relevance Analysis and Neuronal Path Perturbation
However, it faces several key challenges, including accurately implementing unlearning, ensuring privacy protection during the unlearning process, and achieving effective unlearning without significantly compromising model performance.
When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?
While existing unlearning methods take into account the specific characteristics of LLMs, they often suffer from high computational demands, limited applicability, or the risk of catastrophic forgetting.
Query-Efficient Video Adversarial Attack with Stylized Logo
Therefore, to generate adversarial examples with a low budget and to provide them with a higher verisimilitude, we propose a novel black-box video attack framework, called Stylized Logo Attack (SLA).
DreamCar: Leveraging Car-specific Prior for in-the-wild 3D Car Reconstruction
With this dataset, we make the generative model more robust to cars.
QUEEN: Query Unlearning against Model Extraction
To limit the potential threat, QUEEN has sensitivity measurement and outputs perturbation that prevents the adversary from training a piracy model with high performance.
Large Language Models for Link Stealing Attacks Against Graph Neural Networks
The handling of these varying data dimensions posed a challenge in using a single model to effectively conduct link stealing attacks on different datasets.
Update Selective Parameters: Federated Machine Unlearning Based on Model Explanation
However, training data cannot be accessed on the server under the federated learning paradigm, conflicting with the requirements of the centralized unlearning process.
Towards Efficient Target-Level Machine Unlearning Based on Essential Graph
After that, we simultaneously filter parameters that are also important for the remaining targets and use the pruning-based unlearning method, which is a simple but effective solution to remove information about the target that needs to be forgotten.
Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions
We discuss how KD can address the challenges in FL, including privacy protection, data heterogeneity, communication efficiency, and personalization.
Linkage on Security, Privacy and Fairness in Federated Learning: New Balances and New Perspectives
Building upon our observations, we identify the trade-offs between privacy and fairness and between security and fairness within the context of federated learning.
Recent Advances in Federated Learning Driven Large Language Models: A Survey on Architecture, Performance, and Security
Federated Learning (FL) offers a promising paradigm for training Large Language Models (LLMs) in a decentralized manner while preserving data privacy and minimizing communication overhead.
3DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Views
(1) \textbf{High-Volume}: 2, 500 cars are meticulously scanned by 3D scanners, obtaining car images and point clouds with real-world dimensions; (2) \textbf{High-Quality}: Each car is captured in an average of 200 dense, high-resolution 360-degree RGB-D views, enabling high-fidelity 3D reconstruction; (3) \textbf{High-Diversity}: The dataset contains various cars from over 100 brands, collected under three distinct lighting conditions, including reflective, standard, and dark.
Federated Learning with Blockchain-Enhanced Machine Unlearning: A Trustworthy Approach
With the growing need to comply with privacy regulations and respond to user data deletion requests, integrating machine unlearning into IoT-based federated learning has become imperative.
Class Machine Unlearning for Complex Data via Concepts Inference and Data Poisoning
In this paper, to accurately defining the unlearning class of complex data, we apply the definition of Concept, rather than an image feature or a token of text data, to represent the semantic information of unlearning class.
Machine Unlearning via Null Space Calibration
Current research centres on efficient unlearning to erase the influence of data from the model and neglects the subsequent impacts on the remaining data.
The Frontier of Data Erasure: Machine Unlearning for Large Language Models
Large Language Models (LLMs) are foundational to AI advancements, facilitating applications like predictive text generation.
AICAttack: Adversarial Image Captioning Attack with Attention-Based Optimization
This paper presents a novel adversarial attack strategy, AICAttack (Attention-based Image Captioning Attack), designed to attack image captioning models through subtle perturbations on images.
Reinforcement Unlearning
Machine unlearning refers to the process of mitigating the influence of specific training data on machine learning models based on removal requests from data owners.
When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers via Membership Inference Attacks
It leverages the difference in the predictions from both the original and fairness-enhanced models and exploits the observed prediction gaps as attack clues.
Divide and Ensemble: Progressively Learning for the Unknown
In the wheat nutrient deficiencies classification challenge, we present the DividE and EnseMble (DEEM) method for progressive test data predictions.
Generative Adversarial Networks Unlearning
Based on the substitution mechanism and fake label, we propose a cascaded unlearning approach for both item and class unlearning within GAN models, in which the unlearning and learning processes run in a cascaded manner.
Privacy and Fairness in Federated Learning: on the Perspective of Trade-off
Federated learning (FL) has been a hot topic in recent years.
Boosting Model Inversion Attacks with Adversarial Examples
Hence, in this paper, we propose a new training paradigm for a learning-based model inversion attack that can achieve higher attack accuracy in a black-box setting.
Machine Unlearning: A Survey
Machine learning has attracted widespread attention and evolved into an enabling technology for a wide range of highly successful applications, such as intelligent computer vision, speech recognition, medical diagnosis, and more.
Towards Robust GAN-generated Image Detection: a Multi-view Completion Representation
GAN-generated image detection now becomes the first line of defense against the malicious uses of machine-synthesized image manipulations such as deepfakes.
Low-frequency Image Deep Steganography: Manipulate the Frequency Distribution to Hide Secrets with Tenacious Robustness
By avoiding high-frequency artifacts and manipulating the frequency distribution of the embedded feature map, LIDS achieves improved robustness against attacks that distort the high-frequency components of container images.
New Challenges in Reinforcement Learning: A Survey of Security and Privacy
A large number of studies have focused on these security and privacy problems in reinforcement learning.
How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers
As a booming research area in the past decade, deep learning technologies have been driven by big data collected and processed on an unprecedented scale.
Momentum Gradient Descent Federated Learning with Local Differential Privacy
The major challenge is to find a way to guarantee that sensitive personal information is not disclosed while data is published and analyzed.
BABD: A Bitcoin Address Behavior Dataset for Pattern Analysis
Cryptocurrencies are no longer just the preferred option for cybercriminal activities on darknets, due to the increasing adoption in mainstream applications.
Making DeepFakes more spurious: evading deep face forgery detection via trace removal attack
To evaluate the attack efficacy, we crafted heterogeneous security scenarios where the detectors were embedded with different levels of defense and the attackers' background knowledge of data varies.
One Parameter Defense -- Defending against Data Inference Attacks via Differential Privacy
The experimental results show the method to be an effective and timely defense against both membership inference and model inversion attacks with no reduction in accuracy.
Label-only Model Inversion Attack: The Attack that Requires the Least Information
In launching a contemporary model inversion attack, the strategies discussed are generally based on either predicted confidence score vectors, i. e., black-box attacks, or the parameters of a target model, i. e., white-box attacks.
Model Inversion Attack against Transfer Learning: Inverting a Model without Accessing It
However, they may not mean that transfer learning models are impervious to model inversion attacks.
A Lightweight Privacy-Preserving Scheme Using Label-based Pixel Block Mixing for Image Classification in Deep Learning
Experimental findings on the testing set show that our scheme preserves image privacy while maintaining the availability of the training set in the deep learning models.
DP-Image: Differential Privacy for Image Data in Feature Space
The excessive use of images in social networks, government databases, and industrial applications has posed great privacy risks and raised serious concerns from the public.
From Distributed Machine Learning To Federated Learning: In The View Of Data Privacy And Security
Federated learning is an improved version of distributed machine learning that further offloads operations which would usually be performed by a central server.
Distributed, Parallel, and Cluster Computing
Correlated Differential Privacy: Feature Selection in Machine Learning
In this way, the impact of data correlation is relieved with the proposed feature selection scheme, and moreover, the privacy issue of data correlation in learning is guaranteed.
Fairness in Semi-supervised Learning: Unlabeled Data Help to Reduce Discrimination
A set of experiments on real-world and synthetic datasets show that our method is able to use unlabeled data to achieve a better trade-off between accuracy and discrimination.
Fairness Constraints in Semi-supervised Learning
Extensive experiments show that our method is able to achieve fair semi-supervised learning, and reach a better trade-off between accuracy and fairness than fair supervised learning.
Differentially Private Multi-Agent Planning for Logistic-like Problems
To the best of our knowledge, this paper is the first to apply differential privacy to the field of multi-agent planning as a means of preserving the privacy of agents for logistic-like problems.
Generating Image Adversarial Examples by Embedding Digital Watermarks
We devise an efficient mechanism to select host images and watermark images and utilize the improved discrete wavelet transform (DWT) based Patchwork watermarking algorithm with a set of valid hyperparameters to embed digital watermarks from the watermark image dataset into original images for generating image adversarial examples.
Local Differential Privacy and Its Applications: A Comprehensive Survey
Local differential privacy (LDP), as a strong privacy tool, has been widely deployed in the real world in recent years.
Cryptography and Security
More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligence
Artificial Intelligence (AI) has attracted a great deal of attention in recent years.
