PEGASIS: Practical Efficient Class Group Action using 4-dimensional isogeniesPierrick DartoisJonathan Eriksenet al.2025CRYPTO 2025
Shorter, Tighter, FAESTer: Optimizations and Improved (QROM) Analysis for VOLE-in-the-Head SignaturesCarsten BaumWard Beullenset al.2025CRYPTO 2025
Save what must be saved: Secure context switching with SailorNeelu Shivprakash KalaniThomas Bourgeatet al.2025USENIX Security 2025
Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language ModelsGeorge KourItay Nakashet al.2025ACL 2025
A Perspective on LLM Data Generation with Few-shot Examples: from Intent to Kubernetes ManifestAntonino AngiLiubov Nedoshivinaet al.2025ACL 2025
Defensive Prompt Patch: A Robust and Generalizable Defense of Large Language Models against Jailbreak AttacksChen XiongXiangyu Qiet al.2025ACL 2025
Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational AgentsIvoline NgongSwanand Ravindra Kadheet al.2025ACL 2025
Performance of Confidential Computing GPUsAntonio Martınez IbarraJulian James Stephenet al.2025ICDCS 2025
MAD-MAX: Modular And Diverse Malicious AttackMiXtures for Automated LLM Red TeamingStefan SchoepfMuhammad Zaid Hameedet al.2025ICML 2025