Matt Fredrikson
Carnegie Mellon University
H-index: 33
North America-United States
Top articles of Matt Fredrikson
Grounding Neural Inference with Satisfiability Modulo Theories
Advances in Neural Information Processing Systems
2024/2/13
Centroid-Based Learning for Malware Detection and Novel Family Identification
2023/10/13
Effectively Leveraging Capacity for Improved Deterministic Robustness Certification
2023/10/13
Enhancing Neural Network Transparency through Representation Analysis
2023/10/13
Is Certifying Robustness Still Worthwhile?
arXiv preprint arXiv:2310.09361
2023/10/13
Ravi Mangal
H-Index: 8
Zifan Wang
H-Index: 3
Kai Hu
H-Index: 13
Anupam Datta
H-Index: 32
Matt Fredrikson
H-Index: 25
A recipe for improved certifiable robustness: Capacity and data
arXiv preprint arXiv:2310.02513
2023/10/4
Representation engineering: A top-down approach to ai transparency
arXiv preprint arXiv:2310.01405
2023/10/2
Universal and transferable adversarial attacks on aligned language models
arXiv preprint arXiv:2307.15043
2023/7/27
Transfer Attacks and Defenses for Large Language Models on Coding Tasks
arXiv preprint arXiv:2311.13445
2023/11/22
Chi Zhang
H-Index: 2
Zifan Wang
H-Index: 3
Ravi Mangal
H-Index: 8
Matt Fredrikson
H-Index: 25
Limin Jia
H-Index: 19
Robustness Evaluation of Proxy Models against Adversarial Optimization
2023/10/13
Degradation Attacks on Certifiably Robust Neural Networks
2022/11/30
Black-box audits for group distribution shifts
arXiv preprint arXiv:2209.03620
2022/9/8
Samuel Yeom
H-Index: 5
Matt Fredrikson
H-Index: 25
Self-correcting neural networks for safe classification
2022/7/31
Exploring Conceptual Soundness with TruLens
2022/7/20
TEO: Ephemeral ownership for iot devices to provide granular data control
2022/6/27
On the Perils of Cascading Robust Classifiers
arXiv preprint arXiv:2206.00278
2022/6/1
Faithful Explanations for Deep Graph Models
arXiv preprint arXiv:2205.11850
2022/5/24
Privacy-preserving case-based explanations: Enabling visual interpretability by protecting privacy
IEEE Access
2022/3/8
Enhancing the insertion of NOP instructions to obfuscate malware via deep reinforcement learning
Computers & Security
2022/2/1
Matt Fredrikson
H-Index: 25
Quan Le
H-Index: 1
Relaxing local robustness
Advances in Neural Information Processing Systems
2021/12/6
Matt Fredrikson
H-Index: 25