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

Homa Hosseinmardi

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

ResearcherUnclaimed source record
Social and Information Networkscs.CYMachine LearningArtificial IntelligenceCryptography and Securityeess.SPInformation RetrievalMolecular Networksphysics.data-anphysics.soc-ph

Catalog footprint

What is connected

8works
10topics
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

8 published item(s)

preprint2026arXiv

Asking Back: Interaction-Layer Antidistillation Watermarks

Detecting unauthorized knowledge distillation from a deployed LLM API is hard because the defender controls neither the attacker's training pipeline nor the next-token logits. Existing defenses operate on the teacher's output tokens -- biasing the next-token distribution (green-list watermarks, cryptographic schemes, antidistillation sampling) or rewriting outputs after generation. Recent work shows a paraphrasing attacker can strip these signals without losing the underlying knowledge. We propose interaction-layer antidistillation watermarks, which move the trace one layer higher, into the teacher's interaction behavior: the defender wraps the teacher with a system prompt that intermittently induces a behavioral marker -- an explicit follow-up question, a low-frequency variant, or a declarative restatement. An oblivious distiller inherits the behavior, and the defender audits via black-box queries with a human-validated LLM-as-judge (Cohen's kappa = 0.84/0.78 on strong/style rubrics). Across 63 LoRA-distilled students under a Llama-3.3-70B-Instruct teacher (35,343 judged samples), behavioral watermarks transfer at 88.9% (Gemma) / 80.9% (OLMo) / 45.2% (Qwen) relative fidelity (H1, H2). Under non-adaptive DIPPER paraphrasing, robustness decomposes into a teacher-self ceiling (about 66.4%) and student-relative retention of 21-112%, with OLMo preserving the watermark above the teacher itself (H3, F-Amp). Low-density (about 20%) explicit and implicit declarative variants transfer above per-family baseline (H4, F-Style). An N=20 in-lab study (pre-registered Latin-square) shows all marker variants within 0.22 Likert step of baseline; TOST, Friedman, and Bonferroni-Wilcoxon support H5. The interaction layer is a viable design locus for antidistillation watermarking, complementary to token-, model-, and reasoning-trace-layer defenses.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Learning Behavioral Representations from Wearable Sensors

Continuous collection of physiological data from wearable sensors enables temporal characterization of individual behaviors. Understanding the relation between an individual's behavioral patterns and psychological states can help identify strategies to improve quality of life. One challenge in analyzing physiological data is extracting the underlying behavioral states from the temporal sensor signals and interpreting them. Here, we use a non-parametric Bayesian approach to model sensor data from multiple people and discover the dynamic behaviors they share. We apply this method to data collected from sensors worn by a population of hospital workers and show that the learned states can cluster participants into meaningful groups and better predict their cognitive and psychological states. This method offers a way to learn interpretable compact behavioral representations from multivariate sensor signals.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Evaluating Overfit and Underfit in Models of Network Community Structure

A common data mining task on networks is community detection, which seeks an unsupervised decomposition of a network into structural groups based on statistical regularities in the network's connectivity. Although many methods exist, the No Free Lunch theorem for community detection implies that each makes some kind of tradeoff, and no algorithm can be optimal on all inputs. Thus, different algorithms will over or underfit on different inputs, finding more, fewer, or just different communities than is optimal, and evaluation methods that use a metadata partition as a ground truth will produce misleading conclusions about general accuracy. Here, we present a broad evaluation of over and underfitting in community detection, comparing the behavior of 16 state-of-the-art community detection algorithms on a novel and structurally diverse corpus of 406 real-world networks. We find that (i) algorithms vary widely both in the number of communities they find and in their corresponding composition, given the same input, (ii) algorithms can be clustered into distinct high-level groups based on similarities of their outputs on real-world networks, and (iii) these differences induce wide variation in accuracy on link prediction and link description tasks. We introduce a new diagnostic for evaluating overfitting and underfitting in practice, and use it to roughly divide community detection methods into general and specialized learning algorithms. Across methods and inputs, Bayesian techniques based on the stochastic block model and a minimum description length approach to regularization represent the best general learning approach, but can be outperformed under specific circumstances. These results introduce both a theoretically principled approach to evaluate over and underfitting in models of network community structure and a realistic benchmark by which new methods may be evaluated and compared.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Investigating Factors Influencing the Latency of Cyberbullying Detection

Cyberbullying in online social networks has become a critical problem, especially among teenagers who are social networks' prolific users. As a result, researchers have focused on identifying distinguishing features of cyberbullying and developing techniques to automatically detect cyberbullying incidents. While this research has resulted in developing highly accurate classifiers, two key practical issues related to identifying cyberbullying have largely been ignored, namely scalability of cyberbullying detection services and timeliness of raising alerts whenever a cyberbullying incident is suspected. These two issues are the subject of this paper. We propose a multi-stage cyberbullying detection solution that drastically reduces the classification time and the time to raise cyberbullying alerts. The proposed solution is highly scalable, does not sacrifice accuracy for scalability, and is highly responsive in raising alerts. The solution is comprised of three novel components, an initial predictor, a multilevel priority scheduler, and an incremental classification mechanism. We have implemented this solution and utilized data obtained from the Vine online social network to demonstrate the utility of each of these components via a detailed performance evaluation. We show that our complete solution is significantly more scalable and responsive than the current state-of-the-art.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Detection of Cyberbullying Incidents on the Instagram Social Network

Cyberbullying is a growing problem affecting more than half of all American teens. The main goal of this paper is to investigate fundamentally new approaches to understand and automatically detect incidents of cyberbullying over images in Instagram, a media-based mobile social network. To this end, we have collected a sample Instagram data set consisting of images and their associated comments, and designed a labeling study for cyberbullying as well as image content using human labelers at the crowd-sourced Crowdflower Web site. An analysis of the labeled data is then presented, including a study of correlations between different features and cyberbullying as well as cyberaggression. Using the labeled data, we further design and evaluate the accuracy of a classifier to automatically detect incidents of cyberbullying.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Prediction of Cyberbullying Incidents on the Instagram Social Network

Cyberbullying is a growing problem affecting more than half of all American teens. The main goal of this paper is to investigate fundamentally new approaches to understand and automatically detect and predict incidents of cyberbullying in Instagram, a media-based mobile social network. In this work, we have collected a sample data set consisting of Instagram images and their associated comments. We then designed a labeling study and employed human contributors at the crowd-sourced CrowdFlower website to label these media sessions for cyberbullying. A detailed analysis of the labeled data is then presented, including a study of relationships between cyberbullying and a host of features such as cyberaggression, profanity, social graph features, temporal commenting behavior, linguistic content, and image content. Using the labeled data, we further design and evaluate the performance of classifiers to automatically detect and pre- dict incidents of cyberbullying and cyberaggression.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

A Comparison of Common Users across Instagram and Ask.fm to Better Understand Cyberbullying

This paper examines users who are common to two popular online social networks, Instagram and Ask.fm, that are often used for cyberbullying. An analysis of the negativity and positivity of word usage in posts by common users of these two social networks is performed. These results are normalized in comparison to a sample of typical users in both networks. We also examine the posting activity of common user profiles and consider its correlation with negativity. Within the Ask.fm social network, which allows anonymous posts, the relationship between anonymity and negativity is further explored.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Towards Understanding Cyberbullying Behavior in a Semi-Anonymous Social Network

Cyberbullying has emerged as an important and growing social problem, wherein people use online social networks and mobile phones to bully victims with offensive text, images, audio and video on a 247 basis. This paper studies negative user behavior in the Ask.fm social network, a popular new site that has led to many cases of cyberbullying, some leading to suicidal behavior.We examine the occurrence of negative words in Ask.fms question+answer profiles along with the social network of likes of questions+answers. We also examine properties of users with cutting behavior in this social network.

0 citations0 reviewsNo code linkedOpen access