Conference LLM Whisperer: An Inconspicuous Attack to Bias LLM Responses 2025 1-24 Lin W, Gerchanovsky A, Akgul O, Bauer L, Fredrikson M, Wang Z
Conference A RECIPE FOR IMPROVED CERTIFIABLE ROBUSTNESS 2024 • 12th International Conference on Learning Representations, ICLR 2024 Hu K, Leino K, Wang Z, Fredrikson M
Conference Attacks and Defenses for Large Language Models on Coding Tasks 2024 • Proceedings / IEEE International Conference, Automated Software Engineering ; sponsored by IEEE Computer Society, NASA Ames Research Center, in cooperation with AAAI, ACM SIGART and SIGSOFT. IEEE International Automated Software Enginee... • 2268-2272 Zhang C, Wang Z, Zhao R, Mangal R, Fredrikson M, Jia L, Pasareanu CS
Conference Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization 2024 • Advances in Neural Information Processing Systems • 37: Hu K, Yu W, Li Y, Yao T, Li X, Liu W, Yu L, Shen Z, Chen K, Fredrikson M
Conference Improving Alignment and Robustness with Circuit Breakers 2024 • Advances in Neural Information Processing Systems • 37: Zou A, Phan L, Wang J, Duenas D, Lin M, Andriushchenko M, Wang R, Kolter Z, Fredrikson M, Hendrycks D
Preprint Is Certifying $\ell_p$ Robustness Still Worthwhile? 2023 Mangal R, Leino K, Wang Z, Hu K, Yu W, Pasareanu C, Datta A, Fredrikson M
Conference ON THE PERILS OF CASCADING ROBUST CLASSIFIERS 2023 • 11th International Conference on Learning Representations, ICLR 2023 Mangal R, Wang Z, Zhang C, Leino K, Păsăreanu C, Fredrikson M
Preprint Representation Engineering: A Top-Down Approach to AI Transparency 2023 Zou A, Phan L, Chen S, Campbell J, Guo P, Ren R, Pan A, Yin X, Mazeika M, Dombrowski A-K, Goel S, Li N, Byun MJ, Wang Z, Mallen A, Basart S, Koyejo S, Song D, Fredrikson M, Kolter JZ, Hendrycks D
Preprint Transfer Attacks and Defenses for Large Language Models on Coding Tasks 2023 Zhang C, Wang Z, Mangal R, Fredrikson M, Jia L, Pasareanu C
Preprint Universal and Transferable Adversarial Attacks on Aligned Language Models 2023 Zou A, Wang Z, Carlini N, Nasr M, Kolter JZ, Fredrikson M
Preprint Unlocking Deterministic Robustness Certification on ImageNet 2023 Hu K, Zou A, Wang Z, Leino K, Fredrikson M
Conference Unlocking Deterministic Robustness Certification on ImageNet 2023 • Advances in Neural Information Processing Systems Hu K, Zou A, Wang Z, Leino K, Fredrikson M
Conference CONSISTENT COUNTERFACTUALS FOR DEEP MODELS 2022 • ICLR 2022 - 10th International Conference on Learning Representations Black E, Wang Z, Datta A, Fredrikson M
Journal Article Degradation Attacks on Certifiably Robust Neural Networks 2022 • Transactions of Machine Learning Research • 1(1): Leino K, Zhang C, Mangal R, Fredrikson M, Parno B, Pasareanu C
Journal Article Enhancing the insertion of NOP instructions to obfuscate malware via deep reinforcement learning 2022 • Computers and Security • 113: Gibert D, Fredrikson M, Mateu C, Planes J, Le Q
Preprint Faithful Explanations for Deep Graph Models 2022 Wang Z, Yao Y, Zhang C, Zhang H, Kang Y, Joe-Wong C, Fredrikson M, Datta A
Preprint On the Perils of Cascading Robust Classifiers 2022 Mangal R, Wang Z, Zhang C, Leino K, Pasareanu C, Fredrikson M
Journal Article Privacy-Preserving Case-Based Explanations: Enabling Visual Interpretability by Protecting Privacy 2022 • IEEE Access • 10:28333-28347 Montenegro H, Silva W, Gaudio A, Fredrikson M, Smailagic A, Cardoso JS
Conference Protecting user data through ephemeral ownership of IoT devices 2022 620-621 Zhang H, Agarwal Y, Fredrikson M
Conference Robust Models Are More Interpretable Because Attributions Look Normal 2022 • INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162 Wang Z, Fredrikson M, Datta A
Conference SELECTIVE ENSEMBLES FOR CONSISTENT PREDICTIONS 2022 • ICLR 2022 - 10th International Conference on Learning Representations Black E, Leino K, Fredrikson M
Chapter Self-correcting Neural Networks for Safe Classification 2022 • Lecture Notes in Computer Science • 13466:96-130 Leino K, Fromherz A, Mangal R, Fredrikson M, Parno B, Pasareanu C
Conference Automating Audit with Policy Inference 2021 • Proceedings - IEEE Computer Security Foundations Symposium • 406-421 Bichhawat A, Fredrikson M, Yang J
