Hackers hijack AI accounts and servers to fuel new cyber crime boom
Source note: Headlines and standfirsts only; full text is paywalled.
Security researchers warn of surge in ‘LLM-jacking’ attacks targeting companies’ costly AI resources
Every model that read this
| Model | Provider | Stage | Score | Conf. | Latency | Prompt | When |
|---|---|---|---|---|---|---|---|
| Llama 3.3 70B | Meta | analysis | -75 | 80% | 3274ms | v1.0.0 / m1.0.1 | 2026-09-26 12:17 |
| Claude Sonnet 5 | Anthropic | consensus | -45 | 45% | 5623ms | v1.0.0 / m1.0.1 | 2026-09-26 12:17 |
| Gemini 2.5 Flash | consensus | -100 | 80% | 1856ms | v1.0.0 / m1.0.1 | 2026-09-26 12:17 | |
| Mistral Small 3.1 24B | Mistral AI | consensus | -65 | 80% | 7469ms | v1.0.0 / m1.0.1 | 2026-09-26 12:17 |
Hijacking AI accounts and servers fuels cyber crime
This is a headline-only report on a warned trend, not a measured incident with specifics like scale or financial loss. The implication is negative for security but evidence is thin, based on researcher warnings rather than confirmed data.
The article warns of a surge in 'LLM-jacking' where hackers hijack AI accounts and servers for cybercrime. This implies that AI resources are being exploited to facilitate criminal activity, leading to material harm through resource theft and enhanced cyber threats. This represents a significant negative implication for cybersecurity and economic stability.
The article warns of a new type of cybercrime involving AI. This implies increased risk of AI misuse. The evidence is speculative.
Evidence extracted
- Hackers hijack AI accounts and servers
- Surge in 'LLM-jacking' attacks
SOURCE Financial Times: Artificial Intelligence (tier 1)
↓
DOCUMENT be891e24-a87a-41ca-985b-1a857aa714e8
https://ft.com/content/3f406fbe-b72e-488f-9975-5b94e95dfe32
↓
EVIDENCE 2 extracted excerpts
↓
MODEL RUN 4 runs, methodology 1.0.1
↓
SCORE -71 (Strongly adverse)
↓
CONFIDENCE 71%