Related papers: Lara: Lightweight Anonymous Authentication with As…

System and network event logs are essential for security analytics, threat detection, and operational monitoring. However, these logs often contain Personally Identifiable Information (PII), raising significant privacy concerns when shared…

We consider the problem of ON-OFF privacy in which a user is interested in the latest message generated by one of n sources available at a server. The user has the choice to turn privacy ON or OFF depending on whether he wants to hide his…

Artificial Intelligence has become a double edged sword in modern society being both a boon and a bane. While it empowers individuals it also enables malicious actors to perpetrate scams such as fraudulent phone calls and user…

Retrieval-Augmented Generation (RAG) enhances the utility of Large Language Models (LLMs) by retrieving external documents. Since the knowledge databases in RAG are predominantly utilized via cloud services, private data in sensitive…

Noise-based certified machine unlearning currently faces a hard ceiling: the noise magnitude required to certify unlearning typically destroys model utility, particularly for large-scale deletion requests. While leveraging public data is a…

Recent studies have numerically demonstrated the possible advantages of the asynchronous non-orthogonal multiple access (ANOMA) over the conventional synchronous non-orthogonal multiple access (NOMA). The ANOMA makes use of the oversampling…

Biometric data is pervasively captured and analyzed. Using modern machine learning approaches, identity and attribute inferences attacks have proven high accuracy. Anonymizations aim to mitigate such disclosures by modifying data in a way…

Machine unlearning enables the removal of specific data from ML models to uphold the right to be forgotten. While approximate unlearning algorithms offer efficient alternatives to full retraining, this work reveals that they fail to…

Counterfactuals operationalised through algorithmic recourse have become a powerful tool to make artificial intelligence systems explainable. Conceptually, given an individual classified as y -- the factual -- we seek actions such that…

Anonymization is the process of removing or hiding sensitive information in logs. Anonymization allows organizations to share network logs while not exposing sensitive information. However, there is an inherent trade off between the amount…

Instruction fine-tuning of large language models (LLMs) is a powerful method for improving task-specific performance, but it can inadvertently lead to a phenomenon where models generate harmful responses when faced with malicious prompts.…

Privacy auditing provides empirical lower bounds on the differential privacy parameters of learning algorithms. Existing methods, however, require interventional access to the training pipeline, either to retrain multiple times or to…

Considering computer systems, security is the major concern with usability. Security policies need to be developed to protect information from unauthorized access. Passwords and secrete codes used between users and information systems for…

In our data world, a host of not necessarily trusted controllers gather data on individual subjects. To preserve her privacy and, more generally, her informational self-determination, the individual has to be empowered by giving her agency…

Person re-identification (re-id) is a pivotal task within an intelligent surveillance pipeline and there exist numerous re-id frameworks that achieve satisfactory performance in challenging benchmarks. However, these systems struggle to…

The large language model (LLM) powered recommendation paradigm has been proposed to address the limitations of traditional recommender systems, which often struggle to handle cold start users or items with new IDs. Despite its…

Multi-modal retrieval-augmented generation (MRAG) systems retrieve visual evidence from large image corpora to ground the responses of large multi-modal models, yet the retrieved images frequently contain human faces whose identities…

Biometric techniques are often used as an extra security factor in authenticating human users. Numerous biometrics have been proposed and evaluated, each with its own set of benefits and pitfalls. Static biometrics (such as fingerprints)…

Delegating authentication to identity providers like Google or Facebook, while convenient, compromises user privacy. These identity providers can record users' every move; the global identifiers they provide also enable internet-wide…

Many existing systems track aliasing and uniqueness, each with their own trade-off between expressiveness and developer effort. We propose Latte, a new approach that aims to minimize both the amount of annotations and the complexity of…