Beyond Laplace and Gaussian: Exploring the Generalized Gaussian Mechanism for Private Machine Learning

Differential privacy DP is obtained by randomizing a data analysis algorithm, which necessarily introduces a tradeoff between its utility and privacy. Many DP mechanisms are built upon one of two underlying tools: Laplace and Gaussian additive noise mechanisms. We expand the search space of...

Quantum Machine Learning

The meteoric rise of artificial intelligence in recent years has seen machine learning methods become ubiquitous in modern science, technology, and industry. Concurrently, the emergence of programmable quantum computers, coupled with the expectation that large-scale fault-tolerant machines will...

Differential Privacy in Machine Learning: from Symbolic AI to LLMs

Machine learning models should not reveal particular information that is not otherwise accessible. Differential privacy provides a formal framework to mitigate privacy risks by ensuring that the inclusion or exclusion of any single data point does not significantly alter the output of an algorith...

When Forgetting Triggers Backdoors: a Clean Unlearning Attack

Machine unlearning has emerged as a key component in ensuring Right to be Forgotten, enabling the removal of specific data points from trained models. However, even when the unlearning is performed without poisoning the forget-set clean unlearning, it can be exploited for stealthy attacks that...

Towards Reliable Forgetting: a Survey on Machine Unlearning Verification, Challenges, and Future Directions

With growing demands for privacy protection, security, and legal compliance e.g., GDPR, machine unlearning has emerged as a critical technique for ensuring the controllability and regulatory alignment of machine learning models. However, a fundamental challenge in this field lies in effectively...

Algorithmic Approaches to Enhance Safety in Autonomous Vehicles: Minimizing Lane Changes and Merging

The rapid advancements in autonomous vehicle AV technology promise enhanced safety and operational efficiency. However, frequent lane changes and merging maneuvers continue to pose significant safety risks and disrupt traffic flow. This paper introduces the Minimizing Lane Change Algorithm MLCA, ...

Busting the Paper Ballot: Voting Meets Adversarial Machine Learning

We show the security risk associated with using machine learning classifiers in United States election tabulators. The central classification task in election tabulation is deciding whether a mark does or does not appear on a bubble associated to an alternative in a contest on the ballot. Barrett...

Human-Centred AI in FinTech: Developing a User Experience (UX) Research Point of View (PoV) Playbook

Advancements in Artificial Intelligence AI have significantly transformed the financial industry, enabling the development of more personalized and adaptable financial products and services. This research paper explores various instances where Human-Centred AI HCAI has facilitated these...

Systems-Theoretic and Data-Driven Security Analysis in ML-enabled Medical Devices

The integration of AI/ML into medical devices is rapidly transforming healthcare by enhancing diagnostic and treatment facilities. However, this advancement also introduces serious cybersecurity risks due to the use of complex and often opaque models, extensive interconnectivity, interoperability...

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,...

Offensive Robot Cybersecurity

Offensive Robot Cybersecurity introduces a groundbreaking approach by advocating for offensive security methods empowered by means of automation. It emphasizes the necessity of understanding attackers' tactics and identifying vulnerabilities in advance to develop effective defenses, thereby...

A Comprehensive Survey on Underwater Acoustic Target Positioning and Tracking: Progress, Challenges, and Perspectives

Underwater target tracking technology plays a pivotal role in marine resource exploration, environmental monitoring, and national defense security. Given that acoustic waves represent an effective medium for long-distance transmission in aquatic environments, underwater acoustic target tracking h...

CVE-2025-32880

An issue was discovered on COROS PACE 3 devices through 3.0808.0. It implements a function to connect the watch to a WLAN. With WLAN access, the COROS Pace 3 downloads firmware files via HTTP. However, the communication is not encrypted and allows sniffing and machine-in-the-middle attacks...

CVE-2025-32877

An issue was discovered on COROS PACE 3 devices through 3.0808.0. It identifies itself as a device without input or output capabilities, which results in the use of the Just Works pairing method. This method does not implement any authentication, which therefore allows machine-in-the-middle...

CVE-2025-32875

An issue was discovered in the COROS application through 3.8.12 for Android. Bluetooth pairing and bonding is neither initiated nor enforced by the application itself. Also, the watch does not enforce pairing and bonding. As a result, any data transmitted via BLE remains unencrypted, allowing...

OESA-2025-1649 kernel security update

The Linux Kernel, the operating system core itself. Security Fixes: In the Linux kernel, the following vulnerability has been resolved: scsi: target: Fix WRITESAME No Data Buffer crash In newer version of the SBC specs, we have a NDOB bit that indicates there is no data buffer that gets written...

A Common Pool of Privacy Problems: Legal and Technical Lessons from a Large-Scale Web-Scraped Machine Learning Dataset

We investigate the contents of web-scraped data for training AI systems, at sizes where human dataset curators and compilers no longer manually annotate every sample. Building off of prior privacy concerns in machine learning models, we ask: What are the legal privacy implications of web-scraped...

CVE-2025-32875

The CVE-2025-32875 entry concerns the COROS Android app (versions up to 3.8.12). The root issue is that Bluetooth pairing and bonding are neither initiated nor enforced by the app, and the watch also does not enforce them. Consequently, BLE data remains unencrypted, enabling attackers within Blue...

CVE-2025-32877

An issue was discovered on COROS PACE 3 devices through 3.0808.0. It identifies itself as a device without input or output capabilities, which results in the use of the Just Works pairing method. This method does not implement any authentication, which therefore allows machine-in-the-middle...

CVE-2025-32875

An issue was discovered in the COROS application through 3.8.12 for Android. Bluetooth pairing and bonding is neither initiated nor enforced by the application itself. Also, the watch does not enforce pairing and bonding. As a result, any data transmitted via BLE remains unencrypted, allowing...