Security
A rule monitor found about 70% of attacks on AI agents in a test
The authors tell that the monitor also gave an alarm for 29.3% of safe runs.
arxiv.orgClaimed, not confirmed
News category
Security
149 stories, newest first.
Security
An attack on world models can give robots dangerous policies
The authors put malicious prompts in data that looks safe, and the attack works only after a world model uses the data.
arxiv.orgClaimed, not confirmed
Security
A guardrails proxy increases injection recall from 25.0% to 94.5%
The authors found a false-positive rate of 0.1%, and the system limits the model to a closed set of commands.
arxiv.orgClaimed, not confirmed
Security
A new attack agent goes around the guardrails of 4 AI models
The researchers find a success rate of more than 95% for the attack.
arxiv.orgClaimed, not confirmed
Security
The WebMirage attack hijacks web agents in 91.9% of tests
The attack can also get around 3 agent-level defenses.
arxiv.orgClaimed, not confirmed