Transferring Adversarial Robustness Through Robust Representation Matching
- Pratik Vaishnavi
- Kevin Eykholt
- et al.
- 2022
- USENIX Security 2022
Publications
This is our catalog of publications authored by IBM researchers, in collaboration with the global research community. It’s an ever-growing body of work that shows why IBM is one of the most important contributors to modern computing.
Date
Featured collections
Popular topics
10 results for Kevin Eykholt
Adaptive Verifiable Training Using Pairwise Class Similarity
- Shiqi Wang
- Kevin Eykholt
- et al.
- 2021
- AAAI 2021
URET: Universal Robustness Evaluation Toolkit (for Evasion)
- Kevin Eykholt
- Taesung Lee
- et al.
- 2023
- USENIX Security 2023
Accelerating Certified Robustness Training via Knowledge Transfer
- Pratik Vaishnavi
- Kevin Eykholt
- et al.
- 2022
- NeurIPS 2022
Benchmarking the Effect of Poisoning Defenses on the Security and Bias of Deep Learning Models
- Nathalie Baracaldo Angel
- Farhan Ahmed
- et al.
- 2023
- S&P 2023
Benchmarking the Effect of Poisoning Defenses on the Security and Bias of the Final Model
- 2022
- NeurIPS 2022
Ares: A System-Oriented Wargame Framework for Adversarial ML
- Farhan Ahmed
- Pratik Vaishnavi
- et al.
- 2022
- S&P 2022
On the Feasibility of Compressing Certifiably Robust Neural Networks
- Pratik Vaishnavi
- Veena Krish
- et al.
- 2022
- NeurIPS 2022
DeTA: Minimizing Data Leaks in Federated Learning via Decentralized and Trustworthy Aggregation
- Pau-Chen Cheng
- Kevin Eykholt
- et al.
- 2024
- EuroSys 2024
EdgeTorrent: Real-time Temporal Graph Representations for Intrusion Detection
- Isaiah J. King
- Xiaokui Shu
- et al.
- 2023
- RAID 2023