Related papers: The VACCINE Framework for Building DLP Systems
We introduce an end-to-end private deep learning framework, applied to the task of predicting 30-day readmission from electronic health records. By using differential privacy during training and homomorphic encryption during inference, we…
Although differential privacy (DP) is widely regarded as the de facto standard for data privacy, its implementation remains vulnerable to unfaithful execution by servers, particularly in distributed settings. In such cases, servers may…
As language models (LMs) are widely utilized in personalized communication scenarios (e.g., sending emails, writing social media posts) and endowed with a certain level of agency, ensuring they act in accordance with the contextual privacy…
Applying security patches in open source software timely is critical for ensuring the security of downstream applications. However, it is challenging to apply these patches promptly because notifications of patches are often incomplete and…
Methods for proving that concurrent software does not leak its secrets has remained an active topic of research for at least the past four decades. Despite an impressive array of work, the present situation remains highly unsatisfactory.…
Local differential privacy (LDP) is a variant of differential privacy (DP) that avoids the need for a trusted central curator, at the cost of a worse trade-off between privacy and utility. The shuffle model is a way to provide greater…
Public resources and services (e.g., datasets, training platforms, pre-trained models) have been widely adopted to ease the development of Deep Learning-based applications. However, if the third-party providers are untrusted, they can…
With the COVID-19 pandemic entering a second phase and vaccination strategies being applied by countries and governments worldwide, there is an increasing expectation by people to return to normal life. There is currently a debate about…
Large language models (LLMs) remain acutely vulnerable to prompt injection and related jailbreak attacks; heuristic guardrails (rules, filters, LLM judges) are routinely bypassed. We present Contextual Integrity Verification (CIV), an…
Differential Privacy (DP) has emerged as a pivotal approach for safeguarding individual privacy in data analysis, yet its practical adoption is often hindered by challenges in the implementation and communication of DP. This paper presents…
Most deep learning frameworks require users to pool their local data or model updates to a trusted server to train or maintain a global model. The assumption of a trusted server who has access to user information is ill-suited in many…
The widespread use of big data across sectors has raised major privacy concerns, especially when sensitive information is shared or analyzed. Regulations such as GDPR and HIPAA impose strict controls on data handling, making it difficult to…
Humans develop a series of cognitive defenses, known as epistemic vigilance, to combat risks of deception and misinformation from everyday interactions. Developing safeguards for LLMs inspired by this mechanism might be particularly helpful…
Federated data processing (FDP) offers a promising approach for enabling collaborative analysis of sensitive data without centralizing raw datasets. However, real-world adoption remains limited due to the complexity of managing…
Federated Learning (FL) has emerged as a critical paradigm for enabling privacy-preserving machine learning, particularly in regulated sectors such as finance and healthcare. However, standard FL strategies often encounter significant…
We focus in this paper on the problem of configuring and managing network security devices, such as Firewalls, Virtual Private Network (VPN) tunnels, and Intrusion Detection Systems (IDSs). Our proposal is the following. First, we formally…
Copy Detection Patterns (CDPs) are crucial elements in modern security applications, playing a vital role in safeguarding industries such as food, pharmaceuticals, and cosmetics. Current performance evaluations of CDPs predominantly rely on…
Software vulnerabilities remain a critical security challenge, providing entry points for attackers into enterprise networks. Despite advances in security practices, the lack of high-quality datasets capturing diverse exploit behavior…
Data Distribution Service (DDS) is an innovative approach towards communication in ICS/IoT infrastructure and robotics. Being based on the cross-platform and cross-language API to be applicable in any computerised device, it offers the…
Large language models (LLMs) and autonomous coding agents are increasingly used to generate software across a wide range of domains. Yet a core requirement remains unmet: ensuring that generated code is secure without compromising its…