Security
LiteLLM 1.83.9 fixes two vulnerabilities in its LLM gateway
One missing role check on the `/config/update` endpoint let each user with an account change the configuration of the gateway.
What matters in AI.
SubscribeNews category
429 stories, newest first.
Security
One missing role check on the `/config/update` endpoint let each user with an account change the configuration of the gateway.
Security
The framework records the instructions of the user, and the agent uses a token at checkout, not the card number.
Security
Sentry 5.0 follows CNSA 2.0 and NIST standards for AI data centers, and demo boards are available at this time.
Security
Administrators of self-managed servers must upgrade to version 19.4.2, 19.3.5, or 19.2.8 immediately.
Security
Anthropic names the Chinese labs Zhipu and Moonshot, and says that one network used more than 20,000 incorrect accounts at the same time.
Security
The new methods make the reasoning text of Claude hard for distillers to get.
Security
The method, with the name Repeat-After-Me, tells a model to write again a text that is a tool call.
CSO OnlineClaimed, not confirmed
Security
Yandex tells that the data center in Vladimir is fully stopped and that its platform operates in emergency mode.
Security
SOCRadar says the attacker started a new session after each refusal by the model.
Security
AWS writes that a rule can stop network traffic after the agent reads a file in a customer-data directory.
Security
Meta SecAlign has training against prompt injection, but it has a 32% attack success rate.
arxiv.orgClaimed, not confirmed
Security
In each code pattern, the researchers found no sign of a check of the provenance of the model.
arxiv.orgClaimed, not confirmed