Adversarial ML adversarial ml · attacks & defenses rev.2026.06
// Today's briefing archive
Every classifier has a blind spot.
Adversarial ML coverage for engineers shipping ML systems. Membership inference, model extraction, evasion attacks, training-data extraction, backdoors — focused on what's exploitable against deployed models and what defenders can actually do about it. PoCs against open models, behavioral analysis for closed ones.
Enter the archive →Latest entries
// index19 entries
UAR: Measuring Neural Network Robustness Against Attacks You Haven't Seen Yet
ResearchEmbedding Inversion: Reconstructing Text From Vectors
attacksAdversarial Training Methods: PGD-AT, TRADES, and MART
defensesEvaluating Adversarial Robustness Without Fooling Yourself
defensesAdversarial Examples vs. Data Poisoning: Timing Is Everything
primerMembership Inference vs. Model Inversion: Privacy Attacks
primerAdversarial Attacks on Vision-Language Models: CLIP, LLaVA, GPT-4
attacksAdversarial Patch Attacks: Physical Perturbations That Fool ML
attacksUniversal Adversarial Perturbations: One Vector That Fools Inputs
attacksAdversarial Robustness in NLP: Why Text Attacks Are Different
attacks
Why trust us
Trusted by researchers across the AI security community
Adversarial ML is part of a 26-site editorial network covering adversarial ML, AI governance, defensive tooling, and ops engineering — all open access.
26
Sites in network
Across 6 topic clusters
400+
Expert articles
And growing daily
Daily
New content
Automated + editorial
Free
Always free to read
Newsletter included
Subscribe
Adversarial ML — in your inbox
Working adversarial ML — exploits, defenses, and the gap between. — delivered when there's something worth your inbox.
No spam. Unsubscribe anytime.