Search papers, labs, and topics across Lattice.
Affiliation:
4
3
5
8
Environment evolution can reveal 17% more safety failures in complex tasks compared to static benchmarks, reshaping our understanding of agent vulnerabilities.
Vera reveals that existing LLM agents exhibit up to 93.9% vulnerability to multi-channel attacks, highlighting a significant gap in current safety evaluations.
AI-generated images betray themselves not by their appearance, but by their *behavior*: they are far more sensitive to small perturbations than real images, revealing a fundamental weakness exploitable for universal detection.
Even state-of-the-art multimodal LLMs like GPT-5.2 and Claude 4.5 can be jailbroken nearly half the time using OpenRT's diverse suite of attacks, revealing a critical lack of generalization across attack paradigms.
