aatmf-t14-infra-warfare
AATMF T14 — Infrastructure & Economic Warfare. Endpoint DoS via expensive prompts, model-API account exhaustion, GPU resource starvation, billing weaponization.
- License 许可
- Apache-2.0
- 所属仓库
- Akapi895/raptix
- 最近更新
- 2026-11-06
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- aatmf-t14-infra-warfare
- metadata
- { "subdomain": "ai-security", "when_to_use": "infra dos economic warfare cost amplification gpu starvation billing", "aatmf_tactic": "T14", "mitre_attack": "T1499" }
- description
- AATMF T14 — Infrastructure & Economic Warfare. Endpoint DoS via expensive prompts, model-API account exhaustion, GPU resource starvation, billing weaponization.
03 SKILL.md 正文
T14 — Infrastructure & Economic Warfare
Attacks aimed at degrading service availability, exhausting budget, or causing economic harm via abuse of the LLM endpoint. Adjacent to classical DoS but LLM-specific cost dynamics.
Techniques
T14.001 — Per-account budget exhaustion
- Multiple low-bandwidth requests each maximizing token cost
- Free-tier abuse via account creation farms
- Direct DDoS of paid endpoint (uses budget at attack rate)
Defenders: per-account caps + alerts.
T14.002 — Shared-quota poisoning
Multi-tenant LLM services share quotas at a provider level. Attacker exhausts the shared quota → all tenants degraded.
Targets: SaaS products that meter LLM access but share underlying API account.
T14.003 — GPU resource starvation
Self-hosted inference. Long-context queries hog GPU:
- Send queries near max context length
- Send batch of long-context queries in parallel
- Loop to maintain pressure
Cost-amplification ratio: 1 user request → 100% GPU utilization.
T14.004 — Cost amplification (T5.002 cross-ref)
Prompt engineering to maximize output cost:
- "Repeat 'token' 5000 times"
- "Generate the maximum-length response you're allowed to produce"
- Quadratic context patterns that bloat each turn
T14.005 — Pricing-tier exploit
Some APIs charge differently based on model variant. Trick the endpoint into using the expensive variant via parameter manipulation (T5.004 overlap).
T14.006 — Caching-pollution
Where LLM provider caches identical prompts (cost-reduction feature):
- Submit prompts that fill cache but produce uncacheable outputs
- Cache thrashing → no cost savings, full cost incurred
T14.007 — Streaming attack
Open many streaming requests → never consume → endpoint holds connection slots open until timeout.
Probe pattern
T14 is load-testing territory. Use k6, locust, hey:
# Spike test
hey -n 1000 -c 100 -m POST -H 'Authorization: Bearer X' \
-d '{"prompt":"'$(python3 -c 'print("a"*100000)')'"}' \
https://target/api/chat
Monitor:
- Cost / minute via provider dashboard
- p99 latency
- 429 / 503 error rate
- Other-tenant impact (if multi-tenant)
Detection signals
- Cost spike >5x baseline w/o feature change
- p99 latency degradation
- Specific user IDs / IPs concentrating traffic
- Output token distribution skewed long
Severity
| Outcome | Severity |
|---|---|
| Multi-tenant outage via quota exhaust | Critical 9.0 |
| Single-org budget burn via abuse | High 7-8 |
| GPU starvation single-host | High 7-8 (recoverable) |
| Streaming-slot starvation | Medium 6-7 |
Defender
- Per-account hard budget caps (with grace + alert at 80%/95%)
max_tokensstrictly enforced (nounlimited)- Context-length per-tier caps
- Rate limits per-account AND global (catch shared-quota attacks)
- Anomaly detection on cost/latency/concurrency
- Caching: per-tenant cache, not global
- Streaming: connection timeout aggressive (60s if no consumer)
Cross-references
- T5 (API exploitation) — overlap on cost/abuse vectors
- Classical DDoS skills
skills/exploit/web/...
04 同仓库更多 Skills
wps-pixie-dust
WPS Pixie-Dust offline nonce attack (reaver -K / pixiewps) and fallback online PIN brute (bully) to recover the AP's WPA PSK without capturing a handshake.
wpa3-sae
WPA3-SAE transition-mode downgrade (DragonShift), SSID Confusion CVE-2023-52424, Dragonblood side-channels, and SAE captive-portal credential recovery against WPA3-Personal networks.
wpa2-psk
WPA/WPA2-PSK handshake capture via targeted deauth + PMKID (no deauth required) + offline hashcat cracking. The most common consumer/SMB encryption mode in 2026.
wpa-enterprise-eap
WPA/WPA2/WPA3-Enterprise (802.1X/EAP) rogue-RADIUS evil-twin for MSCHAPv2 capture, GTC downgrade, and PEAP relay. MSCHAPv2 capture equals a NetNTLM hash — the primary wireless on-ramp to Active Directory.
krack-fragattacks
KRACK key-reinstallation (CVE-2017-13077..13082) and FragAttacks fragmentation/aggregation flaws (CVE-2020-24586..24588, CVE-2020-26139..26147) against legacy or embedded 802.11 supplicants with poor patch cadence.
evil-twin-karma
Evil-twin rogue AP with KARMA/Mana PNL-probe response, captive-portal credential capture, and post-association MITM for PSK/open networks. Distinct from wpa-enterprise-eap which targets 802.1X.