Adversarial.js – hack neural networks in the browser

What it does

Neural networks achieve superhuman performance in many areas, but they are easily fooled. In the demo above, we can force neural networks to predict anything we want. By adding nearly-invisible noise to an image, we turn "1"s into "9"s, "Stop" signs into "120 km/hr" signs, and dogs into hot dogs. These noisy images are called adversarial examples . They break the integrity of machine learning systems, and the illusion of their superhuman performance. Our world is becoming increasingly automated, yet these systems have strange failure modes. No. Adversarial examples exist for almost every machine learning task: speech recognition , text classification , fraud detection , machine translation…from kennysong.github.io

• GP
  GAN Playground – Play with Generative Adversarial Neural Nets In-Browser2017 · reiinakano.github.io · ▲97
• 
  I am a high school student and I did research on 3D adversarial attacks2019 · arxiv.org · ▲116

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

• 
  Security Training for Developers2016 · hacksplaining.com · ▲128

  Hacksplaining teaches secure coding through interactive lessons where you exploit attacks, then learn fixes. Free. 45+ lessons covering OWASP Top 10 and AI-era threats.

• 
  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…

• 
  TensorFire2017 · tenso.rs · ▲99

  Blazing-fast in-browser neural networks

• 
  hack.css2016 · hackcss.com · ▲174

  The CSS framework for hackers

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 18d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 18d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 20d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 21d ago · stillwet.art

• 
  Beam.win▲378

  Run AI agents on one Mac and use its windows on another

  AI · 5d ago · beam.win

• 
  FastRouter.ai▲364

  Route requests to the right LLM for cost, latency & quality

  AI · 22d ago · fastrouter.ai

• 
  Admin Portal (by WorkOS)▲1,408

  Pre-built wizard for configuring Single Sign-On (SSO/SAML)

  Dev tools · 2020 · workos.com

• 
  Sidekick Browser▲1,050

  A productivity browser for becoming focused and unstoppable

  Work · 2020 · perplexity.ai

• 
  PFPMaker▲1,027

  Create an awesome profile pic from any photo

  Growth · 2020 · pfpmaker.com

• 
  Screenity▲878

  The most powerful screen recorder for Chrome

  Dev tools · 2020 · chromewebstore.google.com

• 
  Notion Timeline▲778

  Plot all your projects chronologically

  Work · 2020 · notion.so

• 
  I Rebuilt MySpace from 2007▲726

  SpaceHey is a retro social network focused on privacy and customizability. It

  Life & fun · 2020 · spacehey.com