Transferring Adversarial Robustness Through Robust Representation MatchingPratik VaishnaviKevin Eykholtet al.2022USENIX Security 2022
Adaptive Verifiable Training Using Pairwise Class SimilarityShiqi WangKevin Eykholtet al.2021AAAI 2021
URET: Universal Robustness Evaluation Toolkit (for Evasion)Kevin EykholtTaesung Leeet al.2023USENIX Security 2023
Accelerating Certified Robustness Training via Knowledge TransferPratik VaishnaviKevin Eykholtet al.2022NeurIPS 2022
Benchmarking the Effect of Poisoning Defenses on the Security and Bias of Deep Learning ModelsNathalie Baracaldo AngelFarhan Ahmedet al.2023S&P 2023
Benchmarking the Effect of Poisoning Defenses on the Security and Bias of the Final ModelNathalie Baracaldo AngelKevin Eykholtet al.2022NeurIPS 2022
Ares: A System-Oriented Wargame Framework for Adversarial MLFarhan AhmedPratik Vaishnaviet al.2022S&P 2022
On the Feasibility of Compressing Certifiably Robust Neural NetworksPratik VaishnaviVeena Krishet al.2022NeurIPS 2022
DeTA: Minimizing Data Leaks in Federated Learning via Decentralized and Trustworthy AggregationPau-Chen ChengKevin Eykholtet al.2024EuroSys 2024
EdgeTorrent: Real-time Temporal Graph Representations for Intrusion DetectionIsaiah J. KingXiaokui Shuet al.2023RAID 2023