Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
2
0
4
Stateful AI agents can be fully hijacked without touching a single model weight or system prompt, but deterministic write-gating across dependency graphs halts 100% of external memory poisoning attacks.
Despite the rise of sophisticated neural models, simple TF-IDF features still dominate in detecting multi-turn SMS phishing attacks, suggesting that lexical cues are surprisingly effective.