Related papers: Auditing without Leaks Despite Curiosity
Simply restricting the computation to non-sensitive part of the data may lead to inferences on sensitive data through data dependencies. Inference control from data dependencies has been studied in the prior work. However, existing…
At present, the review process for material that is exempt from disclosure under the Freedom of Information Act (FOIA) in the United States of America, and under many similar government transparency regimes worldwide, is entirely manual.…
The purpose of accounting audit is to have clear understanding on the financial activities of a company, which can be enhanced by machine learning or reinforcement learning as numeric analysis better than manual analysis can be made. For…
In this paper, we propose an algorithm that targets contamination and eavesdropping adversaries. We consider the case when the number of independent packets available to the eavesdropper is less than the multicast capacity of the network.…
Auditing Large Language Models (LLMs) is a crucial and challenging task. In this study, we focus on auditing black-box LLMs without access to their parameters, only to the provided service. We treat this type of auditing as a black-box…
In enterprise fraud detection, model accuracy alone is insufficient when insiders can tamper with audit logs or bypass approval workflows. Real-world incidents show that fraud often persists not because detection algorithms fail, but…
Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data. Yet, in practice, even models learned with privacy guarantees can inadvertently memorize unique training examples or leak…
In automated complexity analysis, noninterference-based type systems statically guarantee, via soundness, the property that well-typed programs compute functions of a given complexity class, e.g., the class FP of functions computable in…
Adversarial attacks by malicious users that threaten the safety of large language models (LLMs) can be viewed as attempts to infer a target property $T$ that is unknown when an instruction is issued, and becomes knowable only after the…
We propose an operational measure of information leakage in a non-stochastic setting to formalize privacy against a brute-force guessing adversary. We use uncertain variables, non-probabilistic counterparts of random variables, to construct…
Machine learning (ML) is increasingly applied across industries to automate decision-making, but concerns about ethical and legal compliance remain due to limited transparency, fairness, and accountability. Monitoring through logging a…
Simulating a shared register can mask the intricacies of designing algorithms for asynchronous message-passing systems subject to crash failures, since it allows them to run algorithms designed for the simpler shared-memory model. Typically…
In recent years, discussions about fairness in machine learning, AI ethics and algorithm audits have increased. Many entities have developed framework guidance to establish a baseline rubric for fairness and accountability. However, in…
We introduce a privacy measure called statistic maximal leakage that quantifies how much a privacy mechanism leaks about a specific secret, relative to the adversary's prior information about that secret. Statistic maximal leakage is an…
Existing tamper-evident logging systems suffer from high overhead and severe data loss in high-load settings, yet only provide coarse-grained tamper detection. Moreover, installing such systems requires recompiling kernel code. To address…
New regulations and increased awareness of data privacy have led to the deployment of new and more efficient differentially private mechanisms across public institutions and industries. Ensuring the correctness of these mechanisms is…
By filtering the content that users see, social media platforms have the ability to influence users' perceptions and decisions, from their dining choices to their voting preferences. This influence has drawn scrutiny, with many calling for…
Federated Learning presents a way to revolutionize AI applications by eliminating the necessity for data sharing. Yet, research has shown that information can still be extracted during training, making additional privacy-preserving measures…
Indistinguishability properties such as differential privacy bounds or low empirically measured membership inference are widely treated as proxies to show a model is sufficiently protected against broader memorization risks. However, we…
Security, privacy, and fairness have become critical in the era of data science and machine learning. More and more we see that achieving universally secure, private, and fair systems is practically impossible. We have seen for example how…