Adversarial ML

Adversarial ML literacy names crafted inputs that fool classifiers or LLM guards — recognize patterns on YOUR $AI_LAB notes, not attacks on stranger production models.

Adversarial ML• Audio Walkthrough

00:00/03:41

Visual · t32_adversarial_ml

Adversarial ML literacy. $AI_LAB only. Original Cyberlium.

Small perturbations, wrong classification — literacy names adversarial examples so defenders build robustness tests on scoped toys.

Adversarial machine learning crafts inputs — pixel noise, synonym swaps, unicode tricks, or prompt variations — that cause models to misclassify or bypass filters while looking normal to humans. Vision, spam, and content-moderation models are common targets. Defender fix: adversarial training, ensemble models, input normalization, and continuous eval — literacy on paper for $AI_LAB fictional classifiers. Cyberlium names adversarial ML on YOUR $AI_LAB — no crafted attacks against stranger production APIs. Next: Supply Chain Models.

1. Adversarial techniques (named)

Evasion attack: modified input at inference to bypass classifier. Poisoning overlap: training-time perturbations (see data poisoning). Unicode and homoglyph tricks: visually similar characters bypass filters. Prompt variation: paraphrase to evade moderation LLM.

On $AI_LAB, write three technique names with one detection or robustness defense each — fictional toy classifier only.

Command guide

Try these commands — Adversarial techniques (named)

═══ LINUX / macOS (Terminal Practice) ═══

Check system state and user context

Command — copy this

id
whoami
uname -a

Inspect network sockets listening for connections

Command — copy this

ss -tuln 2>/dev/null || netstat -tuln

Audit active processes

Command — copy this

ps aux | grep -v "\[" | head -15

═══ WINDOWS (POWERSHELL) ═══ Query user identity and system information

Command — copy this

whoami /all
Get-ComputerInfo | Select-Object CsName, OsName, OsVersion

Primary tools to practice this lesson: grep, python3. Reference sites: MITRE ATLAS adversarial (https://atlas.mitre.org/); NIST AI RMF Measure (https://www.nist.gov/itl/ai-risk-management-framework); OWASP LLM Top 10 (https://owasp.org/www-project-top-10-for-large-language-model-applications/). Run every command in the box — install first, then the usage lines — only on YOUR lab / program scope.

2. Why adversarial robustness matters for AI security

Safety filters and fraud detectors fail under adversarial input — defenders run red-team eval suites on scoped models with written ROE. OWASP LLM and NIST AI RMF cite robustness testing as control.

Students describe adversarial scenarios on lab notes — never fuzz stranger moderation APIs without authorization.

3. Literacy ≠ stranger model evasion campaigns

Forbidden: running adversarial fuzzers against stranger production moderation or fraud APIs. Allowed: adversarial ML card — three techniques, robustness defense, eval habit on $AI_LAB.

Ship: adversarial ML card for YOUR lab notes. Next: Supply Chain Models.

4. What you ship: adversarial ML card for $AI_LAB

Three techniques, robustness defenses, eval habit. $AI_LAB named. NO stranger API fuzzing. chmod 600.

5. What you record before the next lesson

Date. Adversarial ML card. $AI_LAB named. File t32-m04-l02-adversarial-ml.txt chmod 600.

6. Wrong vs right: stranger SaaS vs YOUR toy LLM

Worked failure — same MSF word, opposite target. Right never needs a café Wi-Fi or classmate laptop.

Wrong: Fuzz stranger content moderation API 'for testing.' Skip robustness eval in lab notes.
Right: Write adversarial ML card for YOUR $AI_LAB notes. Next: Supply Chain Models.

Hands-on Exercise