AdapterSwap: Continuous Training of LLMs with Data Removal and Access-Control Guarantees
29:34
End-to-End Framework using LLMs for Technique Identification and Threat-Actor Attribution
23:32
Defending Large Language Models Against Attacks With Residual Stream Activation Analysis
20:33
PyRIT: A Framework for Security Risk Identification and Red Teaming in Generative AI Systems
31:58
LLM Agents for Vulnerability Identification and Verification of CVEs
1:07:59
Keynote - Acting to Ensure AI Benefits Cyber Defense in a Decade of Technological Surprise
56:44
Jonathan Berant (Tel Aviv University / Google) / Towards Robust Language Model Post-training
28:24
Structure and Semantics-Aware Malware Classification with Vision Transformers
28:15