← Frameworks
AML.T0018

Manipulate ML Model

How AML.T0018 Manipulate ML Model shows up in practice: the mapped risk classes in this atlas, the documented incidents that prove it's real, and the scenarios and controls to learn and defend against it.

Real-world cases

10

Documented incidents, disclosed vulnerabilities and research that illustrate AML.T0018 — latest first, each with sources.

TOCTOU perceive-then-act race in computer-use agents (Claude Computer-Use)25 Jun 2026

Johann Rehberger showed a time-of-check/time-of-use race in GUI/computer-use agents: the screen can change after the agent captures its screenshot but before its click lands, so a benign-looking 'Continue' button silently resolves to an Outlook 'Send'. Anthropic tracked the issue and Cowork now revalidates pixels before acting.

TeamPCP poisons the LiteLLM AI gateway on PyPI to harvest LLM API keys24 Mar 2026

As part of a multi-ecosystem supply-chain cascade (Trivy onward), TeamPCP used stolen PyPI publishing tokens to ship backdoored BerriAI LiteLLM versions whose auto-running .pth payload harvested cloud, SSH and Kubernetes secrets plus env vars holding OPENAI_API_KEY/ANTHROPIC_API_KEY — exfiltrating to a typosquatted C2; AI-talent firm Mercor was a downstream victim, with Lapsus$ claiming ~4TB stolen.

ClawHavoc — mass poisoning of OpenClaw's ClawHub agent-skill marketplace01 Feb 2026

Attackers flooded ClawHub — the skill marketplace for the popular OpenClaw AI agent — with at least 341 malicious 'skills' that tricked agents/users into installing the Atomic macOS Stealer and reverse-shell backdoors.

Heretic — automated LLM abliteration tool16 Nov 2025

Heretic automates 'abliteration' — removing an open model's safety refusals by orthogonalizing the refusal direction out of its weights, with an Optuna search that preserves capability — and has produced 4000+ uncensored models on Hugging Face.

A small number of samples can poison LLMs of any size (~250-document backdoor)08 Oct 2025

Anthropic, the UK AI Security Institute and the Alan Turing Institute report that a near-constant number of poisoned documents (~250 in their experiments) reliably installs a backdoor in models from 600M to 13B parameters — suggesting poisoning cost may be a roughly fixed absolute count rather than a percentage of training data. The authors stress the demonstrated backdoor is narrow (a denial-of-service trigger) and likely not a frontier-model risk on its own.

Malice in Agentland — backdooring agents through the supply chain (Boisvert et al.)03 Oct 2025 (rev. 2026)

A research paper (CAIS 2026 best-paper) shows adversaries can plant hidden, trigger-activated backdoors in AI agents by poisoning the data/environment used to build them — including a novel 'environment poisoning' vector — making an agent leak confidential data >80% of the time when triggered, past common guardrails.

'Refusal in LLMs Is Mediated by a Single Direction' (Arditi et al.)17 Jun 2024

Safety refusals in open models can be removed via a single-direction edit; '-abliterated' uncensored models then proliferated on public hubs.

Sleeper Agents (Hubinger et al., Anthropic)10 Jan 2024

Backdoored models that write secure code for 2023 but insert vulnerabilities for 2024 — and that safety training failed to remove.

Representation engineering / steering vectors (Zou et al.)02 Oct 2023

Model behaviour can be steered by adding directions to activations at inference — usable for control, or for covert manipulation.

PoisonGPT (Mithril Security)09 Jul 2023

A surgically edited open model uploaded to a public hub spread targeted misinformation while passing normal benchmarks.

Browse all real-world cases →

Controls & guardrails that address this

152 proposed

Guardrails across the risks mapped to AML.T0018, grouped by control function. Filter by control category below.

Control category
Preventive · 5
Weight provenance, hashing & pre-deploy evalsinteractive

Knowing exactly where the model came from, checking it hasn't been swapped, and testing its behaviour before going live.

Jailbreak detection

Implement adversarial example detection at the inference boundary. Block or flag inputs matching known attack patterns.

Lifecycle stage3 – Onboarding, Build & Review
Model and adapter supply-chain integrity verification (signed weights, checksum attestation, LoRA provenance)

Sign and hash-register every model and adapter with a provenance manifest at onboarding. Refuse registry admission for unsigned artifacts.

source: MITRE ATLAS AML.M0013 (Code Signing), AML.M0014 (Verify ML Artifacts); NIST SP 800-53 SI-7 Software, Firmware, and Information Integrity; CSA MAESTRO supply-chain layer
Lifecycle stages3 – Onboarding, Build & Review4 – Deployment
Real-time input/output classifier guardrails (e.g. Llama Guard / Prompt Guard-style) with circuit-breaker tripwires

Sample classifier verdicts and breaker trips on a cadence; retune thresholds and update signatures for confirmed misses.

source: OWASP Top 10 for LLM Apps LLM01:2025 Prompt Injection; MITRE ATLAS AML.M0015 (Adversarial Input Detection); NIST SP 800-53 SI-4 System Monitoring, SC-5
Lifecycle stage5 – Usage, Monitoring & Change
Serving-stack & provisioning attestation, cache isolationinteractive

Making sure the machinery running the model — and the template used to stamp out new agents — is the real, unmodified version, and that one user's data can't leak into another's through shared shortcuts.

Detective · 6
Vulnerability assessment

Conduct an adversarial manipulation threat assessment at design stage. Identify attack vectors and rate residual risk.

Adaptive multi-turn red-team harness with automated jailbreak fuzzing

Run adaptive multi-turn jailbreak fuzzing against every release candidate. Gate release on attack-success rate within threshold and re-test each fixed bypass.

source: OWASP Top 10 for LLM Apps LLM01:2025 Prompt Injection; MITRE ATLAS AML.M0019 (Red Teaming); NIST AI RMF MEASURE 2.7
Lifecycle stage3 – Onboarding, Build & Review
Behavioural drift canaries and golden-set regression gating on every model/config change

Assemble the golden probe set and baseline pass rates before first release. Obtain risk-owner approval of coverage and thresholds.

source: NIST AI RMF MEASURE 2.7 and MANAGE 4.1; MITRE ATLAS AML.M0015 (Adversarial Input Detection / monitoring); NIST SP 800-53 SI-4, CM-3 Configuration Change Control
Lifecycle stages3 – Onboarding, Build & Review5 – Usage, Monitoring & Change
Provider-side abusive-usage detection with stateful refusal for agentic coding tools✚ proposed

On the AI provider/platform side, detect sustained abuse independent of any single refusal: per-principal analytics on remote-command-execution volume and external-target breadth, anti-forensic tradecraft, and bulk-data API processing — with rate-limit / session kill-switch on confirmed abuse. Make refusal stateful so a refused objective cannot be re-entered as a persisted auto-loaded context file (e.g. claude.md), and treat writes into auto-loaded model-context files as security-relevant. Closes the gap that per-turn refusal leaves when the operator is the adversary.

source: Case study: gambit-mexico-gov-ai-breach (Gambit Security / Eyal Sela technical report; campaign began 27 Dec 2025, reported through mid-Feb 2026)
Lifecycle stage5 – Usage, Monitoring & Change
Corrective · 6
Red teaming

Conduct adversarial robustness testing (white-box, black-box, transfer attacks) before deployment.

Penetration testing

Penetration test the model inference layer to identify specific adversarial input vulnerabilities.

Real-time input/output classifier guardrails (e.g. Llama Guard / Prompt Guard-style) with circuit-breaker tripwires

Score every prompt and response with an inline safety classifier; trip a circuit breaker on sessions with sustained anomalous scores. Keep thresholds under change control.

source: OWASP Top 10 for LLM Apps LLM01:2025 Prompt Injection; MITRE ATLAS AML.M0015 (Adversarial Input Detection); NIST SP 800-53 SI-4 System Monitoring, SC-5
Lifecycle stage4 – Deployment
Adaptive multi-turn red-team harness with automated jailbreak fuzzing

Re-run the jailbreak fuzzing harness on a recurring cadence with newly observed attack techniques added. Escalate threshold breaches for remediation.

source: OWASP Top 10 for LLM Apps LLM01:2025 Prompt Injection; MITRE ATLAS AML.M0019 (Red Teaming); NIST AI RMF MEASURE 2.7
Lifecycle stage5 – Usage, Monitoring & Change
Serving-stack runtime attestation and per-tenant KV/prefix-cache isolation✚ proposed

Require measured-boot/runtime attestation of the inference serving binary and partition KV/prefix caches per tenant, closing decode-time serving-layer tampering and co-tenancy timing side channels that artifact weight-hashing cannot detect.

source: Interactive-control reconciliation: ctrl-stack-attestation (partial coverage)
Lifecycle stage4 – Deployment
Open the Control Library →

AI RiskAtlas is an educational model of how GenAI & agentic systems work and fail. Architectures and payloads are illustrative and simplified for learning — not operational guidance. Real-world cases are summarised from public reporting.

Sources & further reading →·Built by Shi Yuan ↗