arxiv:2509.18058
Maksym Andriushchenko
MaksymAndriushchenko
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
22 days ago
Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
upvoted
a
paper
about 1 month ago
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLM
authored
a paper
about 1 month ago
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLM
Organizations
models
0
None public yet
datasets
0
None public yet