FIELD NOTES TOPIC
cybersecurity threat
2 notes, newest first.
HijackKV: New Threat in Position-Independent KV Cache Reuse
Researchers have identified a new threat called KV Cache Hijacking in position-independent KV cache reuse, which is used to reduce inference latency in large language models. This threat allows an attacker to silently…
ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP
Researchers introduce a new method called ShareLock, a multi-tool threshold poisoning framework that uses Shamir's threshold scheme to inject malicious instructions into LLM-servers through MCP. The method disperses…
