arXiv research

This paper analyzes privacy threats in federated matrix factorization.

Survey on security and privacy in decentralized federated learning.

Survey on threats to federated learning models.

New method protects whistleblowers from retaliation by ensuring their reports remain private.

Generative text classifiers are most vulnerable to membership inference attacks.

Synth-MIA assesses privacy leakage in synthetic tabular data models.

This paper introduces DPI, a new metric to assess data-copying risk in tabular data.

Unified framework for analyzing model stealing attacks and defenses.

Sensitive inferences and user re-identification are major threats to privacy when raw sensor data from wearable or portable devices are shared with cloud-assisted applications. To mitigate these threats, we propose mechanisms to transform sensor data before sharing them with applications running on users' devices. Thes…

Paper improves privacy for language models against reconstruction attacks.

Large-scale collections of electronic records constitute both an opportunity for the development of more accurate prediction models and a threat for privacy. To limit privacy exposure new privacy-enhancing techniques are emerging such as federated learning which enables large-scale data analysis while avoiding the cent…

Paper introduces privacy-preserving few-shot learning for images.

In this paper, we address the problem of data reconstruction from privacy-protected templates, based on recent concept of sparse ternary coding with ambiguization (STCA). The STCA is a generalization of randomization techniques which includes random projections, lossy quantization, and addition of ambiguization noise t…

Research creates a taxonomy to bridge AI security and regulatory gaps.

Parameter-transfer is a well-known and versatile approach for meta-learning, with applications including few-shot learning, federated learning, and reinforcement learning. However, parameter-transfer algorithms often require sharing models that have been trained on the samples from specific tasks, thus leaving the task…

Normalization layers improve the accuracy of Differentially Private training of deep neural networks.

Survey on privacy issues in deep learning and proposed solutions.

Paper reconstructs training data from a single gradient query.

Proposes a new privacy notion for membership inference attacks on machine learning models.

Smart Meters (SMs) are able to share the power consumption of users with utility providers almost in real-time. These fine-grained signals carry sensitive information about users, which has raised serious concerns from the privacy viewpoint. In this paper, we focus on real-time privacy threats, i.e., potential attacker…

PRIME algorithm estimates mean while ensuring privacy and robustness.

Federated learning facilitates the collaborative training of models without the sharing of raw data. However, recent attacks demonstrate that simply maintaining data locality during training processes does not provide sufficient privacy guarantees. Rather, we need a federated learning system capable of preventing infer…

FedHDPrivacy uses DP to improve FL in IoT, maintaining high accuracy.

Survey examines public views on facial recognition technology.

This paper evaluates and compares gradient leakage attacks in federated learning.

New framework UIFV reconstructs private features in VFL without model details.

Paper develops a method to detect training data used in machine learning models.

Securely analyzes survival data across multiple institutions without revealing individual patient records.

Machine learning algorithms, when applied to sensitive data, pose a distinct threat to privacy. A growing body of prior work demonstrates that models produced by these algorithms may leak specific private information in the training data to an attacker, either through the models' structure or their observable behavior.…

Preventing organizations from Cyber exploits needs timely intelligence about Cyber vulnerabilities and attacks, referred as threats. Cyber threat intelligence can be extracted from various sources including social media platforms where users publish the threat information in real time. Gathering Cyber threat intelligen…

Face recognition models can be inferred from student models, posing privacy risks.

Framework extracts symptoms from EHRs for rapid disease outbreak detection.

Enhanced network threat detection using KG, LLM, and imbalanced learning.

Fawkes protects images from unauthorized facial recognition models.

Deep Neural Network (DNN) workloads are quickly moving from datacenters onto edge devices, for latency, privacy, or energy reasons. While datacenter networks can be protected using conventional cybersecurity measures, edge neural networks bring a host of new security challenges. Unlike classic IoT applications, edge ne…

Reduces risk of model inversion by reducing sensitive feature influence.

We improve image perturbation defenses using a better-defined Wasserstein threat model.

Analysis of an organization's computer network activity is a key component of early detection and mitigation of insider threat, a growing concern for many organizations. Raw system logs are a prototypical example of streaming data that can quickly scale beyond the cognitive power of a human analyst. As a prospective fi…

New method defends against unseen threat models using perceptual adversarial training.

This paper uses deep learning to improve network threat detection in finance.

Bayesian deep learning is recently regarded as an intrinsic way to characterize the weight uncertainty of deep neural networks~(DNNs). Stochastic Gradient Langevin Dynamics~(SGLD) is an effective method to enable Bayesian deep learning on large-scale datasets. Previous theoretical studies have shown various appealing p…

While the last few decades have witnessed a huge body of work devoted to inference and learning in distributed and decentralized setups, much of this work assumes a non-adversarial setting in which individual nodes---apart from occasional statistical failures---operate as intended within the algorithmic framework. In r…

Federated learning performs distributed model training using local data hosted by agents. It shares only model parameter updates for iterative aggregation at the server. Although it is privacy-preserving by design, federated learning is vulnerable to noise corruption of local agents, as demonstrated in the previous stu…

Adversarial attacks have exposed a significant security vulnerability in state-of-the-art machine learning models. Among these models include deep reinforcement learning agents. The existing methods for attacking reinforcement learning agents assume the adversary either has access to the target agent's learned paramete…

Current neural network-based classifiers are susceptible to adversarial examples even in the black-box setting, where the attacker only has query access to the model. In practice, the threat model for real-world systems is often more restrictive than the typical black-box model where the adversary can observe the full …

Insider threat detection is getting an increased concern from academia, industry, and governments due to the growing number of malicious insider incidents. The existing approaches proposed for detecting insider threats still have a common shortcoming, which is the high number of false alarms (false positives). The chal…

Adversarial training yields robust models against a specific threat model, e.g., $L_\infty$ adversarial examples. Typically robustness does not generalize to previously unseen threat models, e.g., other $L_p$ norms, or larger perturbations. Our confidence-calibrated adversarial training (CCAT) tackles this problem by b…

Purveyors of malicious network attacks continue to increase the complexity and the sophistication of their techniques, and their ability to evade detection continues to improve as well. Hence, intrusion detection systems must also evolve to meet these increasingly challenging threats. Machine learning is often used to …