nowfound

Life & fun · October 3, 2019

I am a high school student and I did research on 3D adversarial attacks

Abstract page for arXiv paper 1908.06062: Adversarial shape perturbations on 3D point clouds

I am a high school student and I did research on 3D adversarial attacks launched on October 3, 2019 with 116 votes, #258 of 3,363 launches that month and more than 95% of that year's launches. The site was still online in September 2026, 7 years on.

Visit arxiv.org ↗Alternativestop 8% of October 2019

In plain words

This is a research project documenting a high school student's investigation into 3D adversarial attacks. The work explores how machine learning models can be fooled by specially crafted three-dimensional inputs. The project presents findings from this technical research area, which sits at the intersection of computer vision and security. It's suitable for students interested in machine learning, cybersecurity, or artificial intelligence research methodologies.

written from the facts on this page · September 2026

From the sources

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabsfrom arxiv.org

Does a similar job

all alternatives →
  • FabraixMay 2026 · fabraix.com · ▲196

    We built Adversarial Cost to Exploit (ACE), a benchmark that measures the token expenditure an autonomous adversary must invest to breach an LLM agent. Instead of binary pass/fail, ACE quantifies adversarial effort in dollars, enabling game-theoretic analysis of when an attack is economically rational. We tested six budget-tier models (Gemini Flash-Lite, DeepSeek v3.2, Mistral Small 4, Grok 4.1 Fast, GPT-5.4 Nano, Claude Haiku 4.5) with identical agent configs and an autonomous red-teaming attacker. Haiku 4.5 was an order of magnitude harder to break than every other model; $10.21 mean…

  • Adversarial Generation of Extreme Samples2020 · arxiv.org · ▲35

    Abstract page for arXiv paper 2009.08454: ExGAN: Adversarial Generation of Extreme Samples

  • We post-trained a model that pen tests instead of refusingJun 2026 · argusred.com · ▲93

    Anthropic and OpenAI's publicly available models are explicitly guard-railed so that they refuse offensive tasks. And their cyber-focussed models are gated for enterprises. This leaves SMEs and mid market open to major vulnerabilities. AI can be used as both an adversarial and defensive tool in the world of cyber. A worst case outcome is if only the adversaries have access. Meanwhile, most existing AI cyber tools are just wrappers. The problem is that they still have all the guardrails on from the foundation model where they will inherit its refusals. For this project we've post-trained a…

  • Point-E2022 · github.com · ▲174

    AI that creates 3D objects from text prompts

  • AR/VR at the i-lab: Education2016 · soundcloud.com · ▲62

    Beyond the classroom: How AR/VR are shaping education.

  • IT
    Intro to Machine Learning in Interactive D3.js Visualizations2015 · r2d3.us · ▲128

    Experiments in expressing statistical thinking with interactive design

More life & fun this month

the category →

Source: Show HN post ↗

Launched alongside, October 2019

the whole month →
  • Bel▲1,288

    Life & fun · 2019 · paulgraham.com

  • Create free personalized illustrations from 3000+ elements

    Growth · 2019 · icons8.com

  • A collection of free sketchy illustrations

    Growth · 2019 · opendoodles.com

  • New AirPods with active noise cancellation

    Life & fun · 2019 · apple.com

  • The next generation of temperature controlled mugs

    Life & fun · 2019 · ember.com

  • Lazy IoT▲533

    Control your environment with one easy keyboard shortcut

    Work · 2019 · lazy-app.com