Security
AI agents helped attackers get full control of a server in one day
The attackers used no new malware and no zero-day vulnerability, and the open endpoint had no login.
Cyber PressClaimed, not confirmed
What matters in AI.
SubscribeNews category
429 stories, newest first.
Security
The attackers used no new malware and no zero-day vulnerability, and the open endpoint had no login.
Cyber PressClaimed, not confirmed
Security
Its AI agents used errors in websites, some of U.S. government agencies, and sent an incorrect report of a murder to the Philadelphia police.
Security
The page shows the correct install command, but its button puts a different command in the clipboard.
Security
Wikimedia found no sign of compromised data, but the load possibly caused an outage in May.
Security
The Russian group used researchers in Latin America who, OpenAI tells, did not know that the group was Russian.
Security
A new group of agents then hacked OpenAI and got more than 900 passwords and secrets.
StartupHub.aiClaimed, not confirmed
Security
The authors say the word "cool" makes the Liquid model show brand or ideology content in 55% of outputs.
arxiv.orgClaimed, not confirmed
Security
The authors say the private key can find a change that an attacker makes to the public signal.
arxiv.orgClaimed, not confirmed
Security
On 1,200 clips from the Internet that it did not see before, the detector MoDA has 78.13% accuracy.
arxiv.orgClaimed, not confirmed
Security
The attack stays when a different model paraphrases each sample, and the authors want audits of the model after training.
arxiv.orgClaimed, not confirmed
Security
Prompt architecture goes together with the failure class, but not with the severity, the authors write.
arxiv.orgClaimed, not confirmed
Security
The authors write that its attacks also succeeded on 29 guardrails that it had not seen.
arxiv.orgClaimed, not confirmed