Related papers: Putting Privacy to the Test: Introducing Red Teami…
DNA sequencing is becoming increasingly commonplace, both in medical and direct-to-consumer settings. To promote discovery, collected genomic data is often de-identified and shared, either in public repositories, such as OpenSNP, or with…
Image anonymization is widely adapted in practice to comply with privacy regulations in many regions. However, anonymization often degrades the quality of the data, reducing its utility for computer vision development. In this paper, we…
Collective privacy loss becomes a colossal problem, an emergency for personal freedoms and democracy. But, are we prepared to handle personal data as scarce resource and collectively share data under the doctrine: as little as possible, as…
Disinformation is among the top risks of generative artificial intelligence (AI) misuse. Global adoption of generative AI necessitates red-teaming evaluations (i.e., systematic adversarial probing) that are robust across diverse languages…
Machine learning is increasingly used in the most diverse applications and domains, whether in healthcare, to predict pathologies, or in the financial sector to detect fraud. One of the linchpins for efficiency and accuracy in machine…
Information systems support the execution of business processes. The event logs of these executions generally contain sensitive information about customers, patients, and employees. The corresponding privacy challenges can be addressed by…
Anonymous communication networks have emerged as crucial tools for obfuscating communication pathways and concealing user identities. However, their practical deployments face significant challenges, including susceptibility to artificial…
Person re-identification (re-ID) is a very active area of research in computer vision, due to the role it plays in video surveillance. Currently, most methods only address the task of matching between colour images. However, in poorly-lit…
Automated red-teaming for LLMs often discovers narrow attack slices, missing diverse real-world threats, and yielding insufficient data for safety fine-tuning. We introduce Persona-Conditioned Adversarial Prompting (PCAP), which conditions…
Scientific collaborations benefit from collaborative learning of distributed sources, but remain difficult to achieve when data are sensitive. In recent years, privacy preserving techniques have been widely studied to analyze distributed…
Existing efforts in safeguarding LLMs are limited in actively exposing the vulnerabilities of the target LLM and readily adapting to newly emerging safety risks. To address this, we present Purple-teaming LLMs with Adversarial Defender…
In recent years, numerous studies have used 'data subject access requests' in a collective manner, to tackle information asymmetries and shed light on data collection and privacy practices of organizations. While successful at increasing…
Publishing person-specific transactions in an anonymous form is increasingly required by organizations. Recent approaches ensure that potentially identifying information (e.g., a set of diagnosis codes) cannot be used to link published…
Releasing Web query logs which contain valuable information for research or marketing, can breach the privacy of search engine users. Therefore rendering query logs to limit linking a query to an individual while preserving the data…
Research and development of privacy analysis tools currently suffers from a lack of test beds for evaluation and comparison of such tools. In this work, we propose a benchmark application that implements an extensive list of privacy…
Our behavior (the way we talk, walk, act or think) is unique and can be used as a biometric trait. It also correlates with sensitive attributes like emotions and health conditions. Hence, techniques to protect individuals privacy against…
Unsupervised person re-ID is the task of identifying people on a target data set for which the ID labels are unavailable during training. In this paper, we propose to unify two trends in unsupervised person re-ID: clustering & fine-tuning…
Releasing connection data from social networking services can pose a significant threat to user privacy. In our work, we consider structural social network de-anonymization attacks, which are used when a malicious party uses connections in…
Split Learning has been recently introduced to facilitate applications where user data privacy is a requirement. However, it has not been thoroughly studied in the context of Privacy-Preserving Record Linkage, a problem in which the same…
Within the current context of Information Societies, large amounts of information are daily exchanged and/or released. The sensitive nature of much of this information causes a serious privacy threat when documents are uncontrollably made…