Empirical auditing has emerged as a means of catching some of the flaws in the implementation of privacy-preserving algorithms. Existing auditing mechanisms, however, are either computationally inefficient requiring multiple runs of the machine learning algorithms or suboptimal in calculating an empirical privacy. In this work, we present a tight and efficient auditing procedure and analysis that can effectively assess the privacy of mechanisms. Our approach is efficient; similar to the recent work of Steinke, Nasr, and Jagielski (2023), our auditing procedure leverages the randomness of examples in the input dataset and requires only a single run of the target mechanism. And it is more accurate; we provide a novel analysis that enables us to achieve tight empirical privacy estimates by using the hypothesized $f$-DP curve of the mechanism, which provides a more accurate measure of privacy than the traditional $\epsilon,\delta$ differential privacy parameters. We use our auditing procure and analysis to obtain empirical privacy, demonstrating that our auditing procedure delivers tighter privacy estimates.

The potential of transformer-based LLMs risks being hindered by privacy concerns due to their reliance on extensive datasets, possibly including sensitive information. Regulatory measures like GDPR and CCPA call for using robust auditing tools to address potential privacy issues, with Membership Inference Attacks (MIA) being the primary method for assessing LLMs' privacy risks. Differently from traditional MIA approaches, often requiring computationally intensive training of additional models, this paper introduces an efficient methodology that generates \textit{noisy neighbors} for a target sample by adding stochastic noise in the embedding space, requiring operating the target model in inference mode only. Our findings demonstrate that this approach closely matches the effectiveness of employing shadow models, showing its usability in practical privacy auditing scenarios.

This paper studies federated linear contextual bandits under the notion of user-level differential privacy (DP). We first introduce a unified federated bandits framework that can accommodate various definitions of DP in the sequential decision-making setting. We then formally introduce user-level central DP (CDP) and local DP (LDP) in the federated bandits framework, and investigate the fundamental trade-offs between the learning regrets and the corresponding DP guarantees in a federated linear contextual bandits model. For CDP, we propose a federated algorithm termed as $\texttt{ROBIN}$ and show that it is near-optimal in terms of the number of clients $M$ and the privacy budget $\varepsilon$ by deriving nearly-matching upper and lower regret bounds when user-level DP is satisfied. For LDP, we obtain several lower bounds, indicating that learning under user-level $(\varepsilon,\delta)$-LDP must suffer a regret blow-up factor at least $\min\{1/\varepsilon,M\}$ or $\min\{1/\sqrt{\varepsilon},\sqrt{M}\}$ under different conditions.

Privacy-Preserving machine learning (PPML) can help us train and deploy models that utilize private information. In particular, on-device Machine Learning allows us to completely avoid sharing information with a third-party server during inference. However, on-device models are typically less accurate when compared to the server counterparts due to the fact that (1) they typically only rely on a small set of on-device features and (2) they need to be small enough to run efficiently on end-user devices. Split Learning (SL) is a promising approach that can overcome these limitations. In SL, a large machine learning model is divided into two parts, with the bigger part residing on the server-side and a smaller part executing on-device, aiming to incorporate the private features. However, end-to-end training of such models requires exchanging gradients at the cut layer, which might encode private features or labels. In this paper, we provide insights into potential privacy risks associated with SL and introduce a novel attack method, EXACT, to reconstruct private information. Furthermore, we also investigate the effectiveness of various mitigation strategies. Our results indicate that the gradients significantly improve the attacker's effectiveness in all three datasets reaching almost 100% reconstruction accuracy for some features. However, a small amount of differential privacy (DP) is quite effective in mitigating this risk without causing significant training degradation.

Robustness of machine learning models is critical for security related applications, where real-world adversaries are uniquely focused on evading neural network based detectors. Prior work mainly focus on crafting adversarial examples with small uniform norm-bounded perturbations across features to maintain the requirement of imperceptibility. Although such approaches are valid for images, uniform perturbations do not result in realistic adversarial examples in domains such as malware, finance, and social networks. For these types of applications, features typically have some semantically meaningful dependencies. The key idea of our proposed approach is to enable non-uniform perturbations that can adequately represent these feature dependencies during adversarial training. We propose using characteristics of the empirical data distribution, both on correlations between the features and the importance of the features themselves. Using experimental datasets for malware classification, credit risk prediction, and spam detection, we show that our approach is more robust to real-world attacks. Our approach can be adapted to other domains where non-uniform perturbations more accurately represent realistic adversarial examples.

Collaborative machine learning and related techniques such as distributed and federated learning allow multiple participants, each with his own training dataset, to build a joint model. Participants train local models and periodically exchange model parameters or gradient updates computed during the training. We demonstrate that the training data used by participants in collaborative learning is vulnerable to inference attacks. First, we show that an adversarial participant can infer the presence of exact data points in others' training data (i.e., membership inference). Then, we demonstrate that the adversary can infer properties that hold only for a subset of the training data and are independent of the properties that the joint model aims to capture. We evaluate the efficacy of our attacks on a variety of tasks, datasets, and learning configurations, and conclude with a discussion of possible defenses.

Collaborative security initiatives are increasingly often advocated to improve timeliness and effectiveness of threat mitigation. Among these, collaborative predictive blacklisting (CPB) aims to forecast attack sources based on alerts contributed by multiple organizations that might be targeted in similar ways. Alas, CPB proposals thus far have only focused on improving hit counts, but overlooked the impact of collaboration on false positives and false negatives. Moreover, sharing threat intelligence often prompts important privacy, confidentiality, and liability issues. In this paper, we first provide a comprehensive measurement analysis of two state-of-the-art CPB systems: one that uses a trusted central party to collect alerts [Soldo et al., Infocom'10] and a peer-to-peer one relying on controlled data sharing [Freudiger et al., DIMVA'15], studying the impact of collaboration on both correct and incorrect predictions. Then, we present a novel privacy-friendly approach that significantly improves over previous work, achieving a better balance of true and false positive rates, while minimizing information disclosure. Finally, we present an extension that allows our system to scale to very large numbers of organizations.