Search papers, labs, and topics across Lattice.
Affiliation:
2
0
4
1
All tested GUI agents are alarmingly vulnerable to environmental injection attacks, with success rates reaching over 66%, revealing a pressing need for improved safety measures.
DeepSight offers an all-in-one open-source toolkit for LLM safety, promising to move beyond black-box evaluations and provide white-box insights into internal mechanisms.
