Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion

Large language models remain vulnerable to jailbreak attacks -- inputs designed to bypass safety mechanisms and elicit harmful responses -- despite advances in alignment and instruction tuning. We propose Head-Masked Nullspace Steering HMNS, a circuit-level intervention that i identifies attentio...

A Critical Analysis of the Medibank Health Data Breach and Differential Privacy Solutions

This paper critically examines the 2022 Medibank health insurance data breach, which exposed sensitive medical records of 9.7 million individuals due to unencrypted storage, centralized access, and the absence of privacy-preserving analytics. To address these vulnerabilities, we propose an...

C-AAE: Compressively Anonymizing Autoencoders for Privacy-Preserving Activity Recognition in Healthcare Sensor Streams

Wearable accelerometers and gyroscopes encode fine-grained behavioural signatures that can be exploited to re-identify users, making privacy protection essential for healthcare applications. We introduce C-AAE, a compressive anonymizing autoencoder that marries an Anonymizing AutoEncoder AAE with...

Restoring Gaussian Blurred Face Images for Deanonymization Attacks

Gaussian blur is widely used to blur human faces in sensitive photos before the photos are posted on the Internet. However, it is unclear to what extent the blurred faces can be restored and used to re-identify the person, especially under a high-blurring setting. In this paper, we explore this...

Breaking Anonymity at Scale: Re-Identifying the Trajectories of 100K Real Users in Japan

Mobility traces represent a critical class of personal data, often subjected to privacy-preserving transformations before public release. In this study, we analyze the anonymized Yjmob100k dataset, which captures the trajectories of 100,000 users in Japan, and demonstrate how existing anonymizati...

CVE-2020-12858

Non-reinitialisation of random data in the advertising payload in COVIDSafe v1.0.15 and v1.0.16 allows a remote attacker to re-identify Android devices running COVIDSafe by scanning for their advertising beacons...

CVE-2020-12857

Caching of GATT characteristic values TempID in COVIDSafe v1.0.15 and v1.0.16 allows a remote attacker to long-term re-identify an Android device running COVIDSafe...

CVE-2020-12856

OpenTrace, as used in COVIDSafe through v1.0.17, TraceTogether, ABTraceTogether, and other applications on iOS and Android, allows remote attackers to conduct long-term re-identification attacks and possibly have unspecified other impact, because of how Bluetooth is used...