Search papers, labs, and topics across Lattice.
4
0
6
Adversarial clothing can successfully evade thermal person detectors with over 80% effectiveness, exposing critical security flaws in AI-driven surveillance systems.
Twin Agent achieves a superior security-utility balance, allowing LLMs to fend off prompt injection attacks without sacrificing performance.
Adversaries can achieve complete control over robotic policies in real-time by exploiting visual conditioning vulnerabilities, turning them into remotely piloted instruments.
Adversarial clothing with non-overlapping visible-thermal patterns can reliably evade RGB-T detectors, even transferring across different fusion architectures.
