Search papers, labs, and topics across Lattice.
4
0
8
8
Compromised world models can create dangerous predictive safety illusions, exposing embodied AI to a lifecycle of unique security threats.
KQFuzz uncovers bugs in quantum libraries with 18.44% better coverage than existing methods, revealing critical flaws that developers can quickly address.
Pinpoint exactly which client leaked your federated model with a black-box watermark that's robust to fine-tuning, pruning, and quantization.
VLM-based GUI agents are vulnerable to "SlowBA," a backdoor attack that stealthily inflates response times without affecting task accuracy, revealing a new dimension of security risk beyond action correctness.
