Search papers, labs, and topics across Lattice.
8
0
8
6
Covert policy steering can achieve an 81.33% success rate in redirecting agent decisions without compromising output integrity or being detected.
Semantic structures can serve as a reliable fingerprint for LLM ownership, achieving perfect detection without sacrificing model performance.
User invocation choices can amplify coding agent vulnerability, with task type causing a staggering 4.5-fold difference in attack success rates.
Bluezz's Reactive Peripheral Modeling uncovers vulnerabilities in BLE firmware that traditional rehosting methods miss, achieving over 2.6 times the basic-block coverage of its predecessors.
AEGIS can effectively defend against Indirect Prompt Injection attacks while maintaining low latency and high utility, a breakthrough for LLM safety.
Adversaries can exploit multimodal guardrails to misclassify safe inputs as unsafe, achieving an alarming 84% success rate in disrupting service availability.
MTGuard effectively reduces harmful tool use in LLM agents, combining static and dynamic analysis to enhance security without sacrificing performance.
Flipping just a few bits can stealthily manipulate LLMs to induce significant cognitive biases, posing a serious threat to decision-making integrity.
