Attacking Interpretable NLP Systems

Studies have shown that machine learning systems are vulnerable to adversarial examples in theory and practice. Where previous attacks have focused mainly on visual models that exploit the difference between human and machine perception, text-based models have also fallen victim to these attacks...

A Privacy-Centric Approach: Scalable and Secure Federated Learning Enabled by Hybrid Homomorphic Encryption

Federated Learning FL enables collaborative model training without sharing raw data, making it a promising approach for privacy-sensitive domains. Despite its potential, FL faces significant challenges, particularly in terms of communication overhead and data privacy. Privacy-preserving Technique...

Privacy-Preserving Drone Navigation through Homomorphic Encryption for Collision Avoidance

As drones increasingly deliver packages in neighborhoods, concerns about collisions arise. One solution is to share flight paths within a specific zip code, but this compromises business privacy by revealing delivery routes. For example, it could disclose which stores send packages to certain...

SynthGuard: Redefining Synthetic Data Generation with a Scalable and Privacy-Preserving Workflow Framework

The growing reliance on data-driven applications in sectors such as healthcare, finance, and law enforcement underscores the need for secure, privacy-preserving, and scalable mechanisms for data generation and sharing. Synthetic data generation SDG has emerged as a promising approach but often...

DEBIAN-CVE-2025-49630

In certain proxy configurations, a denial of service attack against Apache HTTP Server versions 2.4.26 through to 2.4.63 can be triggered by untrusted clients causing an assertion in modproxyhttp2. Configurations affected are a reverse proxy is configured for an HTTP/2 backend, with...

Improper Preservation of Permissions

Overview pyload-ng is a The free and open-source Download Manager written in pure Python Affected versions of this package are vulnerable to Improper Preservation of Permissions via the host header. An attacker can gain unauthorized access and create arbitrary packages by sending crafted requests...

Asynchronous Event Error-Minimizing Noise for Safeguarding Event Dataset

With more event datasets being released online, safeguarding the event dataset against unauthorized usage has become a serious concern for data owners. Unlearnable Examples are proposed to prevent the unauthorized exploitation of image datasets. However, it's unclear how to create unlearnable...

Novel Blockchain-Based Protocols for Electronic Voting and Auctions

Programmable blockchains have long been a hot research topic given their tremendous use in decentralized applications. Smart contracts, using blockchains as their underlying technology, inherit the desired properties such as verifiability, immutability, and transparency, which make it a great sui...

Client Clustering Meets Knowledge Sharing: Enhancing Privacy and Robustness in Personalized Peer-To-Peer Learning

The growing adoption of Artificial Intelligence AI in Internet of Things IoT ecosystems has intensified the need for personalized learning methods that can operate efficiently and privately across heterogeneous, resource-constrained devices. However, enabling effective personalized learning in...

Empowering Digital Agriculture: a Privacy-Preserving Framework for Data Sharing and Collaborative Research

Data-driven agriculture, which integrates technology and data into agricultural practices, has the potential to improve crop yield, disease resilience, and long-term soil health. However, privacy concerns, such as adverse pricing, discrimination, and resource manipulation, deter farmers from...

Verifiable Unlearning on Edge

Machine learning providers commonly distribute global models to edge devices, which subsequently personalize these models using local data. However, issues such as copyright infringements, biases, or regulatory requirements may require the verifiable removal of certain data samples across all edg...

HE-LRM: Encrypted Deep Learning Recommendation Models Using Fully Homomorphic Encryption

Fully Homomorphic Encryption FHE is an encryption scheme that not only encrypts data but also allows for computations to be applied directly on the encrypted data. While computationally expensive, FHE can enable privacy-preserving neural inference in the client-server setting: a client encrypts...

Privacy-Preserving Federated Learning against Malicious Clients Based on Verifiable Functional Encryption

Federated learning is a promising distributed learning paradigm that enables collaborative model training without exposing local client data, thereby protect data privacy. However, it also brings new threats and challenges. The advancement of model inversion attacks has rendered the plaintext...

Free Privacy Protection for Wireless Federated Learning: Enjoy It or Suffer from It?

Inherent communication noises have the potential to preserve privacy for wireless federated learning WFL but have been overlooked in digital communication systems predominantly using floating-point number standards, e.g., IEEE 754, for data storage and transmission. This is due to the potentially...

PDLRecover: Privacy-preserving Decentralized Model Recovery with Machine Unlearning

Decentralized learning is vulnerable to poison attacks, where malicious clients manipulate local updates to degrade global model performance. Existing defenses mainly detect and filter malicious models, aiming to prevent a limited number of attackers from corrupting the global model. However,...

EBS-CFL: Efficient and Byzantine-robust Secure Clustered Federated Learning

Despite federated learning FL's potential in collaborative learning, its performance has deteriorated due to the data heterogeneity of distributed users. Recently, clustered federated learning CFL has emerged to address this challenge by partitioning users into clusters according to their...

CVE-2024-7586 Insertion of Sensitive Information into Log File in GitLab

An issue was discovered in GitLab EE affecting all versions starting from 17.0 prior to 17.0.6, starting from 17.1 prior to 17.1.4, and starting from 17.2 prior to 17.2.2, where webhook deletion audit log preserved auth credentials...

Privacy-Preserving LLM Interaction with Socratic Chain-Of-Thought Reasoning and Homomorphically Encrypted Vector Databases

Large language models LLMs are increasingly used as personal agents, accessing sensitive user data such as calendars, emails, and medical records. Users currently face a trade-off: They can send private records, many of which are stored in remote databases, to powerful but untrusted LLM providers...

AndroIDS : Android-Based Intrusion Detection System Using Federated Learning

The exponential growth of android-based mobile IoT systems has significantly increased the susceptibility of devices to cyberattacks, particularly in smart homes, UAVs, and other connected mobile environments. This article presents a federated learning-based intrusion detection framework called...

Learning Obfuscations of LLM Embedding Sequences: Stained Glass Transform

The high cost of ownership of AI compute infrastructure and challenges of robust serving of large language models LLMs has led to a surge in managed Model-as-a-service deployments. Even when enterprises choose on-premises deployments, the compute infrastructure is typically shared across many tea...