adversarial-robustness-toolbox
Build or review adversarial-ML experiments with Adversarial Robustness Toolbox (ART): estimator adapters, evasion, poisoning, membership inference, or model extraction.
v2026.11.13-21cd5683 installs+3 in 7 days39 StarsMITsynced 11 hours ago
Install
No NotHoly CLI yet? Install it first.
$ curl -fsSL https://notholy.com/install.sh | sh$ notholy skills install aeondave/adversarial-robustness-toolboxWrites to ~/.notholy/skills after checking the signature and the SHA-256.
SignatureSigned, ed25519
Packageba0a8279…323efe80
ba0a82791b9e…71a8323efe805 files · 10.1 KBScanMedium4 findings
- Executable script shipped with the skillassets/cpu_evasion_smoke.py
- injection.no_confirmationreferences/estimator-contract.md:3
- injection.no_confirmationreferences/evasion-evaluation.md:40
Sourcegithub.com/AeonDave/malskill/tree/main/ai/adversarial-robustness-toolbox@21cd568
Use ART to implement a bounded experiment against an explicitly authorized model and dataset; ART is an API, not evidence that a model is robust or vulnerable. Pin the installed ART version and check the matching source before relying on API behavior. This guide is grounded in ART 1.20.1, tag commit cbc47a890a191809baa292992761030e7f46ab18.
Workflow and evidence contract
- Define model access, attacker knowledge, eligible inputs, data splits, perturbation or query budget, and success condition before choosing an attack.
- Wrap the actual model with an ART estimator that exposes the interfaces required by the selected attack. Verify input domain, shape, labels, outputs, loss/gradient behavior, and clipping in that wrapper.
- Keep training, tuning, and final evaluation data distinct. Record ART and dependency versions, estimator/backend, attack parameters, seeds, and any query accounting.
- Check generated data against finite-value, shape, domain/clip, and stated perturbation-budget invariants. Report clean performance and attack metrics with explicit numerators and denominators. A result from one model, split, seed, or attack is not a general robustness claim.
For each report, include: (a) art.__version__ and relevant framework versions; (b) model/estimator type and input/output contract; (c) preprocessing and clip domain; (d) threat model, attack/access mode, norm and epsilon units or query/training-data budget; (e) clean baseline, metric definition and denominator, attack parameters, seed, measured perturbation/query counts, and limitations. Separate source-established API facts from behavior observed in the run.
Load the focused reference
- Adapter selection, preprocessing, loss gradients, output scores/logits, clipping, or an ART version change: references/estimator-contract.md.
- White-box evasion with FGM/PGD or a defensible perturbation/query-budget metric: references/evasion-evaluation.md.
- Authorized poisoning, membership-inference/privacy, or model-extraction workflow: references/privacy-poisoning-extraction.md.
- Reproducible CPU FGM/PGD API and invariant smoke test, without downloads or external models: assets/cpu_evasion_smoke.py.
For challenge artifacts and challenge-specific success oracles, load AI/ML CTF instead of copying its broader playbooks here; load this skill only for ART-specific adapter or API work.
Files in this version
assets/16.4 KB
- cpu_evasion_smoke.py6.4 KB
references/321.5 KB
- estimator-contract.md8.3 KB
- evasion-evaluation.md8.0 KB
- privacy-poisoning-extraction.md5.2 KB
- SKILL.md3.0 KB
Permissions
| Permission | Declared | Found by the scan |
|---|---|---|
| Reads files | No | No |
| Writes files | Yes | Yes |
| Runs shell commands | Yes | Yes |
| Uses the network | Yes | Yes |
| Uses connectors | No | No |
| Drives a browser | No | No |
Scan findings
Reviewed on Nov 13, 2026
- MediumFile · Executable script shipped with the skillassets/cpu_evasion_smoke.py
- MediumPrompt injection · injection.no_confirmationreferences/estimator-contract.md:3
- MediumPrompt injection · injection.no_confirmationreferences/evasion-evaluation.md:40
- InfoLink · Links to outside domains
A clean scan lowers the risk but does not prove a package is safe. Read what you install.
| Version | Published | Commit | SHA-256 | Signature | Permission change |
|---|---|---|---|---|---|
| v2026.11.13-21cd568 | Nov 13, 2026 | 21cd568 | ba0a8279 | Signed | – |
More from AeonDave
All from this publisherMore in AI, agents and MCP
See the category- fal-assetsrehan-remade/fal-assets5
- ai-system-prompt-leakagenoorqureshi/ai-system-prompt-leakage4
- ai-prompt-injectionnoorqureshi/ai-prompt-injection4
- testing-prompt-injection-in-rag-pipelinesmukul975/testing-prompt-injection-in-rag-pipelines4
- implementing-llm-guardrails-for-securitymukul975/implementing-llm-guardrails-for-security4
- defending-llms-with-guardrailsmukul975/defending-llms-with-guardrails4
Ask anything your scope allows.
Create an account, add credits and ask the first question in the chat or the terminal.
- 1/3
Create the account
Individual or company. You can switch to a company later without losing balance or keys.
IndividualCompany - 2/3
Add credits
By card. Pay per token, no subscription.
$5.00minimum deposit - 3/3
Ask
In the chat, or install the CLI and run notholy login in your terminal.
$ notholy login