AI Service Proxies - AI Security Technique
AI Security TechniqueAdversaries may utilize commercial proxy services that resell access to AI services such as frontier model APIs. This infrastructure can be used to conduct large-scale campaigns to perform Exfiltration via AI Inference API via distillation. Adversaries may also use this infrastructure to Generate Malicious Commands for offensive cyber operations, or to generate con...
Overview
A source-backed snapshot of this AI security technique.
Adversaries may utilize commercial proxy services that resell access to AI services such as frontier model APIs.
This infrastructure can be used to conduct large-scale campaigns to perform Exfiltration via AI Inference API via distillation. Adversaries may also use this infrastructure to Generate Malicious Commands for offensive cyber operations, or to generate content for Spearphishing via Social Engineering LLM.
Commercial AI service proxies distribute traffic from different accounts and various cloud platforms. The mix of traffic can make malicious activity difficult to detect and block [1].
Malicious actors conduct LLM Jacking attacks to gain access to victim accounts which they resell access to in their proxy services [2].
References
- [1] https://www.anthropic.com/news/detecting-and-preventing-distillation-attacks
- [2] https://sysdig.com/blog/llmjacking-stolen-cloud-credentials-used-in-new-ai-attack/
Technique details
Identifiers, maturity, and source taxonomy for this technique.
- ATLAS ID
- AML.T0008.005
- Maturity
- realized
- Priority score
- 65
Attack flow
How to read the public records connected to this technique.
Impact
Why this technique may deserve attention in the current dataset.
- Evidence levelrealized
- Mapped defenses0 ATLAS mitigation records
- Public examples1 linked case study records
- Research risks5 related MIT AI Risk records above the confidence threshold
- Vulnerabilities0 linked CVE records
Mitigations
Defenses that may help against this attack.
Case studies
Examples from public reports and exercises.
Model Distillation Campaigns Targeting Anthropic Claude
Anthropic uncovered campaigns to extract Claude’s capabilities carried out by the three Chinese AI Labs: DeepSeek, Moonshot, and MiniMax. Collectively, these campaigns used approximately 24,000 accounts and 16 million queries. They used model distillation to train their own models on the outputs of Claude in an attempt to replicate Claude’s capabilities such as agentic reasoning, code generation, tool use, and computer use.
As outlined in Anthropic's report, model distillation was leveraged as a means for these labs to undermine Anthropic's export controls.[1] Distilled models lack the safeguards that prevent bad actors from using frontier models for malicious purposes such as the bioweapon development, disinformation, offensive cyber operations, and mass surveillance.
References
Source evidence
Original public records and references for this page.
Original source
Original source links
Open the public records and source datasets used for this page.