BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Elisa Bertino

Elisa Bertino appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Cryptography and SecurityArtificial Intelligencecs.CYInformation RetrievalMachine LearningNetworking and Internet ArchitectureDatabasesHuman-Computer InteractionSocial and Information Networks

Catalog footprint

What is connected

10works
9topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

10 published item(s)

preprint2026arXiv

A Survey of Agentic AI and Cybersecurity: Challenges, Opportunities and Use-case Prototypes

Agentic AI marks an important transition from single-step generative models to systems capable of reasoning, planning, acting, and adapting over long-lasting tasks. By integrating memory, tool use, and iterative decision cycles, these systems enable continuous, autonomous workflows in real-world environments. This survey examines the implications of agentic AI for cybersecurity. On the defensive side, agentic capabilities enable continuous monitoring, autonomous incident response, adaptive threat hunting, and fraud detection at scale. Conversely, the same properties amplify adversarial power by accelerating reconnaissance, exploitation, coordination, and social-engineering attacks. These dual-use dynamics expose fundamental gaps in existing governance, assurance, and accountability mechanisms, which were largely designed for non-autonomous and short-lived AI systems. To address these challenges, we survey emerging threat models, security frameworks, and evaluation pipelines tailored to agentic systems, and analyze systemic risks including agent collusion, cascading failures, oversight evasion, and memory poisoning. Finally, we present three representative use-case implementations that illustrate how agentic AI behaves in practical cybersecurity workflows, and how design choices shape reliability, safety, and operational effectiveness.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Information Theoretic Adversarial Training of Large Language Models

Large language models (LLMs) remain vulnerable to adversarial prompting despite advances in alignment and safety, often exhibiting harmful behaviors under novel attack strategies. While adversarial training can improve robustness, existing approaches are computationally expensive and difficult to scale. Recent continuous adversarial training methods, such as Continuous adversarial training (CAT) and Continuous Adversarial Preference Optimization (CAPO), address this challenge by leveraging gradient-based perturbations in the embedding space, enabling more efficient and expressive attacks. Building on this paradigm, we propose WARDEN, a distributionally robust adversarial training framework for LLMs that dynamically reweights adversarial examples through an f -divergence ambiguity set around the empirical training distribution. Our method optimizes the worst-case adversarial loss within a divergence ball around the empirical data distribution, automatically emphasizing harder adversarial examples. Using the convex dual formulation, the objective reduces to a log-sum-exp form under the KL divergence, with a dynamical parameter controlling the strength of reweighting. This study leads to a new class of information-theoretic objectives that significantly reduce attack success rates while maintaining model utility. Across multiple LLMs and attack settings, WARDEN substantially reduces attack success rates with computational and utility costs comparable to CAT-, CAPO-, and MixAT-based baselines, making it a practical approach for scalable robust alignment.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Are Your Sensitive Attributes Private? Novel Model Inversion Attribute Inference Attacks on Classification Models

Increasing use of machine learning (ML) technologies in privacy-sensitive domains such as medical diagnoses, lifestyle predictions, and business decisions highlights the need to better understand if these ML technologies are introducing leakage of sensitive and proprietary training data. In this paper, we focus on model inversion attacks where the adversary knows non-sensitive attributes about records in the training data and aims to infer the value of a sensitive attribute unknown to the adversary, using only black-box access to the target classification model. We first devise a novel confidence score-based model inversion attribute inference attack that significantly outperforms the state-of-the-art. We then introduce a label-only model inversion attack that relies only on the model's predicted labels but still matches our confidence score-based attack in terms of attack effectiveness. We also extend our attacks to the scenario where some of the other (non-sensitive) attributes of a target record are unknown to the adversary. We evaluate our attacks on two types of machine learning models, decision tree and deep neural network, trained on three real datasets. Moreover, we empirically demonstrate the disparate vulnerability of model inversion attacks, i.e., specific groups in the training dataset (grouped by gender, race, etc.) could be more vulnerable to model inversion attacks.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Computing Research Challenges in Next Generation Wireless Networking

By all measures, wireless networking has seen explosive growth over the past decade. Fourth Generation Long Term Evolution (4G LTE) cellular technology has increased the bandwidth available for smartphones, in essence, delivering broadband speeds to mobile devices. The most recent 5G technology is further enhancing the transmission speeds and cell capacity, as well as, reducing latency through the use of different radio technologies and is expected to provide Internet connections that are an order of magnitude faster than 4G LTE. Technology continues to advance rapidly, however, and the next generation, 6G, is already being envisioned. 6G will make possible a wide range of powerful, new applications including holographic telepresence, telehealth, remote education, ubiquitous robotics and autonomous vehicles, smart cities and communities (IoT), and advanced manufacturing (Industry 4.0, sometimes referred to as the Fourth Industrial Revolution), to name but a few. The advances we will see begin at the hardware level and extend all the way to the top of the software "stack." Artificial Intelligence (AI) will also start playing a greater role in the development and management of wireless networking infrastructure by becoming embedded in applications throughout all levels of the network. The resulting benefits to society will be enormous. At the same time these exciting new wireless capabilities are appearing rapidly on the horizon, a broad range of research challenges loom ahead. These stem from the ever-increasing complexity of the hardware and software systems, along with the need to provide infrastructure that is robust and secure while simultaneously protecting the privacy of users. Here we outline some of those challenges and provide recommendations for the research that needs to be done to address them.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

5G Security and Privacy: A Research Roadmap

Cellular networks represent a critical infrastructure and their security is thus crucial. 5G - the latest generation of cellular networks - combines different technologies to increase capacity, reduce latency, and save energy. Due to its complexity and scale, however, ensuring its security is extremely challenging. In this white paper, we outline recent approaches supporting systematic analyses of 4G LTE and 5G protocols and their related defenses and introduce an initial security and privacy roadmap, covering different research challenges, including formal and comprehensive analyses of cellular protocols as defined by the standardization groups, verification of the software implementing the protocols, the design of robust defenses, and application and device security.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Differentially Private $k$-Means Clustering

There are two broad approaches for differentially private data analysis. The interactive approach aims at developing customized differentially private algorithms for various data mining tasks. The non-interactive approach aims at developing differentially private algorithms that can output a synopsis of the input dataset, which can then be used to support various data mining tasks. In this paper we study the tradeoff of interactive vs. non-interactive approaches and propose a hybrid approach that combines interactive and non-interactive, using $k$-means clustering as an example. In the hybrid approach to differentially private $k$-means clustering, one first uses a non-interactive mechanism to publish a synopsis of the input dataset, then applies the standard $k$-means clustering algorithm to learn $k$ cluster centroids, and finally uses an interactive approach to further improve these cluster centroids. We analyze the error behavior of both non-interactive and interactive approaches and use such analysis to decide how to allocate privacy budget between the non-interactive step and the interactive step. Results from extensive experiments support our analysis and demonstrate the effectiveness of our approach.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Lightweight and Secure Two-Party Range Queries over Outsourced Encrypted Databases

With the many benefits of cloud computing, an entity may want to outsource its data and their related analytics tasks to a cloud. When data are sensitive, it is in the interest of the entity to outsource encrypted data to the cloud; however, this limits the types of operations that can be performed on the cloud side. Especially, evaluating queries over the encrypted data stored on the cloud without the entity performing any computation and without ever decrypting the data become a very challenging problem. In this paper, we propose solutions to conduct range queries over outsourced encrypted data. The existing methods leak valuable information to the cloud which can violate the security guarantee of the underlying encryption schemes. In general, the main security primitive used to evaluate range queries is secure comparison (SC) of encrypted integers. However, we observe that the existing SC protocols are not very efficient. To this end, we first propose a novel SC scheme that takes encrypted integers and outputs encrypted comparison result. We empirically show its practical advantage over the current state-of-the-art. We then utilize the proposed SC scheme to construct two new secure range query protocols. Our protocols protect data confidentiality, privacy of user's query, and also preserve the semantic security of the encrypted data; therefore, they are more secure than the existing protocols. Furthermore, our second protocol is lightweight at the user end, and it can allow an authorized user to use any device with limited storage and computing capability to perform the range queries over outsourced encrypted data.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Privacy-Preserving and Outsourced Multi-User k-Means Clustering

Many techniques for privacy-preserving data mining (PPDM) have been investigated over the past decade. Often, the entities involved in the data mining process are end-users or organizations with limited computing and storage resources. As a result, such entities may want to refrain from participating in the PPDM process. To overcome this issue and to take many other benefits of cloud computing, outsourcing PPDM tasks to the cloud environment has recently gained special attention. We consider the scenario where n entities outsource their databases (in encrypted format) to the cloud and ask the cloud to perform the clustering task on their combined data in a privacy-preserving manner. We term such a process as privacy-preserving and outsourced distributed clustering (PPODC). In this paper, we propose a novel and efficient solution to the PPODC problem based on k-means clustering algorithm. The main novelty of our solution lies in avoiding the secure division operations required in computing cluster centers altogether through an efficient transformation technique. Our solution builds the clusters securely in an iterative fashion and returns the final cluster centers to all entities when a pre-determined termination condition holds. The proposed solution protects data confidentiality of all the participating entities under the standard semi-honest model. To the best of our knowledge, ours is the first work to discuss and propose a comprehensive solution to the PPODC problem that incurs negligible cost on the participating entities. We theoretically estimate both the computation and communication costs of the proposed protocol and also demonstrate its practical value through experiments on a real dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2012arXiv

An Analytic Approach to People Evaluation in Crowdsourcing Systems

Worker selection is a significant and challenging issue in crowdsourcing systems. Such selection is usually based on an assessment of the reputation of the individual workers participating in such systems. However, assessing the credibility and adequacy of such calculated reputation is a real challenge. In this paper, we propose an analytic model which leverages the values of the tasks completed, the credibility of the evaluators of the results of the tasks and time of evaluation of the results of these tasks in order to calculate an accurate and credible reputation rank of participating workers and fairness rank for evaluators. The model has been implemented and experimentally validated.

0 citations0 reviewsNo code linkedOpen access
preprint2012arXiv

Detecting, Representing and Querying Collusion in Online Rating Systems

Online rating systems are subject to malicious behaviors mainly by posting unfair rating scores. Users may try to individually or collaboratively promote or demote a product. Collaborating unfair rating 'collusion' is more damaging than individual unfair rating. Although collusion detection in general has been widely studied, identifying collusion groups in online rating systems is less studied and needs more investigation. In this paper, we study impact of collusion in online rating systems and asses their susceptibility to collusion attacks. The proposed model uses a frequent itemset mining algorithm to detect candidate collusion groups. Then, several indicators are used for identifying collusion groups and for estimating how damaging such colluding groups might be. Also, we propose an algorithm for finding possible collusive subgroup inside larger groups which are not identified as collusive. The model has been implemented and we present results of experimental evaluation of our methodology.

0 citations0 reviewsNo code linkedOpen access