Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
4
0
6
40
It is argued that self-modifying coding agents must be designed to be more resilient to such attacks, and properties of the vulnerability, benchmark, model, and agent scaffolding that are sufficient to enable a benchmark poisoning attack are distill.
User-level permissions in AI agents are not just a feature; they are essential for mitigating risks like unauthorized transactions and data leaks.
Users adapt their AI detection strategies in real-time, reflecting both the evolution of generative models and shifting social dynamics.
Existing AI agent permissioning schemes are hard to compare, so this paper provides a formal foundation and reveals a fundamental conflict between training data confidentiality and agent completeness.