Related papers: Privacy Policy Enforcement Guardrails for Data-Sen…

This paper introduces BRIES, a novel compound AI architecture designed to detect and measure the effectiveness of persuasion attacks across information environments. We present a system with specialized agents: a Twister that generates…

Out-of-distribution generalization in reinforcement learning is hard to diagnose when benchmark shifts mix dynamics, observations, goals, and rewards. We address this with Tape, a controlled benchmark that isolates latent rule-shift in…

We revisit the problem of generating synthetic data under differential privacy. To address the core limitations of marginal-based methods, we propose the Private Adaptive Generative Adversarial Network with Bayes Network Structure…

In clinical research, the lack of events of interest often necessitates imbalanced learning. One approach to resolve this obstacle is data integration or sharing, but due to privacy concerns neither is practical. Therefore, there is an…

Software applications have become an omnipresent part of modern society. The consequent privacy policies of these applications play a significant role in informing customers how their personal information is collected, stored, and used.…

We propose a new framework of synthesizing data using deep generative models in a differentially private manner. Within our framework, sensitive data are sanitized with rigorous privacy guarantees in a one-shot fashion, such that training…

This paper extends the Classification Error Gauge (x-CEG) framework, originally developed for measuring the privacy-utility trade-off in tabular datasets, to privacy auditing of Large Language Models (LLMs). We propose LLM-CEG, a systematic…

Autonomous experimental systems are increasingly used in materials research to accelerate scientific discovery, but their performance is often limited by low-quality, noisy data. This issue is especially problematic in data-intensive…

This paper studies privacy-preserving resilient vector consensus in multi-agent systems against faulty agents, where normal agents can achieve consensus within the convex hull of their initial states while protecting state vectors from…

Machine learning has shown promise in network intrusion detection systems, yet its performance often degrades due to concept drift and imbalanced data. These challenges are compounded by the labor-intensive process of labeling network…

Conformal prediction (CP) provides sets of candidate classes with a guaranteed probability of containing the true class. However, it typically relies on a calibration set with clean labels. We address privacy-sensitive scenarios where the…

With the recent remarkable advancement of large language models (LLMs), there has been a growing interest in utilizing them in the domains with highly sensitive data that lies outside their training data. For this purpose,…

Multi-tenant retrieval-augmented generation (RAG) services advertise per-account differential privacy as the operative leakage boundary: each account's queries are guaranteed to satisfy $(\varepsilon_{\text{acc}}, \delta_{\text{acc}})$-DP…

Composition theorems are general and powerful tools that facilitate privacy accounting across multiple data accesses from per-access privacy bounds. However they often result in weaker bounds compared with end-to-end analysis. Two popular…

AI systems in healthcare research have shown potential to increase patient throughput and assist clinicians, yet progress is constrained by limited access to real patient data. To address this issue, we present a zero-shot, knowledge-guided…

Today's massive scale of data collection coupled with recent surges of consumer data leaks has led to increased attention towards data privacy and related risks. Conventional data privacy protection systems focus on reducing custodial risk…

Probabilistic Face Embeddings (PFE) can improve face recognition performance in unconstrained scenarios by integrating data uncertainty into the feature representation. However, existing PFE methods tend to be over-confident in estimating…

Large Language Models (LLMs) hold promise for advancing legal practice by automating complex tasks and improving access to justice. However, their adoption is limited by concerns over client confidentiality, especially when lawyers include…

Reliable detection of personally identifiable information (PII) is increasingly important across modern data-processing systems, yet the task remains difficult: PII spans are heterogeneous, locale-dependent, context-sensitive, and often…

We study spectral graph clustering under edge differential privacy. We propose a matrix shuffling mechanism that combines randomized edge flipping with a random permutation of the adjacency matrix. While edge flipping alone provides only a…