Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2009.03822

A First Look at Zoombombing

Chen Ling·Utkucan Balcı·Jeremy Blackburn·Gianluca Stringhini
View original source ↗Read source document ↗Export metadata ↓

Abstract

Online meeting tools like Zoom and Google Meet have become central to our professional, educational, and personal lives. This has opened up new opportunities for large scale harassment. In particular, a phenomenon known as zoombombing has emerged, in which aggressors join online meetings with the goal of disrupting them and harassing their participants. In this paper, we conduct the first data-driven analysis of calls for zoombombing attacks on social media. We identify ten popular online meeting tools and extract posts containing meeting invitations to these platforms on a mainstream social network, Twitter, and on a fringe community known for organizing coordinated attacks against online users, 4chan. We then perform manual annotation to identify posts that are calling for zoombombing attacks, and apply thematic analysis to develop a codebook to better characterize the discussion surrounding calls for zoombombing. During the first seven months of 2020, we identify over 200 calls for zoombombing between Twitter and 4chan, and analyze these calls both quantitatively and qualitatively. Our findings indicate that the vast majority of calls for zoombombing are not made by attackers stumbling upon meeting invitations or bruteforcing their meeting ID, but rather by insiders who have legitimate access to these meetings, particularly students in high school and college classes. This has important security implications, because it makes common protections against zoombombing, such as password protection, ineffective. We also find instances of insiders instructing attackers to adopt the names of legitimate participants in the class to avoid detection, making countermeasures like setting up a waiting room and vetting participants less effective. Based on these observations, we argue that the only effective defense against zoombombing is creating unique join links for each participant.

Explore related subjects

cs.CY

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Chen Ling, Utkucan Balcı, Jeremy Blackburn, Gianluca Stringhini. 2020-09-08. A First Look at Zoombombing. https://arxiv.org/abs/2009.03822

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Initial results of the Digital Consciousness Model

Artificially intelligent systems have become remarkably sophisticated. They hold conversations, write essays, and seem to understand context in ways that surprise even their creators. This raises a crucial question: Are we creating systems that are conscious? The Digital Consciousness Model (DCM) is a first attempt to assess the evidence for consciousness in AI systems in a systematic, probabilistic way. It provides a shared framework for comparing different AIs and biological organisms, and for tracking how the evidence changes over time as AI develops. Instead of adopting a single theory of consciousness, it incorporates a range of leading theories and perspectives - acknowledging that experts disagree fundamentally about what consciousness is and what conditions are necessary for it. This report describes the structure and initial results of the Digital Consciousness Model. Overall, we find that the evidence is against 2024 LLMs being conscious, but the evidence against 2024 LLMs being conscious is not decisive. The evidence against LLM consciousness is much weaker than the evidence against consciousness in simpler AI systems.

cs.CY↗
arXiv2026

Efficient Safety Benchmarking via Item Response Theory

Safety benchmarks for language models are typically evaluated using static paradigms that treat all items as equally informative for all models, an assumption that is particularly problematic for adversarial, highly heterogeneous safety items. Applied in full to modern benchmark suites, current evaluation procedures would require on the order of $10^5$ responses, most of which provide little ranking signal. We analyze six widely used safety benchmarks and make three contributions toward more efficient safety evaluation. First, we show that Item Response Theory (IRT) recovers interpretable structure on safety benchmarks, with ability estimates resolving differences among models that cluster at the ceiling of raw safety metrics. Second, we show that adaptive item selection, which dynamically chooses informative items for each model based on its responses, approximates full-benchmark rankings (Spearman's $ρ>$ 0.90), reducing evaluation cost by at least 80% on every benchmark where this threshold is attainable, and by up to 99.9%, achieved on AIR-Bench 2024. Third, we introduce a practical procedure for extracting a fixed, informative subset of items reusable across models, a static alternative to adaptive selection with savings of 80--99.8% across benchmarks. Together, these results establish that psychometric methods enable benchmark-aware reductions in evaluation costs across the safety evaluation pipeline.

cs.CY↗
arXiv2026

Beyond the Last Truffula Tree: SustainAI - A Water-Aware, Closed-Loop Framework for Environmentally Accountable AI

As artificial intelligence (AI) becomes embedded in everyday life, its environmental footprint, particularly water consumption remains largely invisible. While energy and carbon impacts are widely recognized, the substantial freshwater demands of data center cooling and electricity generation receive little attention. To address this gap, we introduce SustainAI, a water-aware, closed-loop framework incorporating environmental accountability into AI deployment. SustainAI integrates real-time water metering, a hallucination-aware penalty model, and a water-aware routing algorithm that accounts for regional water stress. Evaluated via Small Language Models (SLMs) extracting health misinformation, results reveal an 11-fold variation in water footprint across geographically distributed data centers (0.0477 mL to 0.5360 mL per inference). Across 1,335 inference runs, the system consumed approximately 399 mL of water but produced only 240 correct outputs, demonstrating that substantial resources are spent on inaccurate responses. Crucially, SustainAI extends beyond technical optimization through a Care by Design lens, framing AI sustainability around relational ethics, regional equity, and ecological stewardship. By combining water monitoring, adaptive accountability, and Care by Design principles, SustainAI provides a practical foundation for integrating ethical care and environmental responsibility into AI infrastructure design and lifecycle management.

cs.CY↗