
Publications
2023
Generating Scenarios from High-Level Specifications for Object Rearrangement Tasks Proceedings Article
In: pp. 11420-11427, 2023.
Human Uncertainty in Concept-Based AI Systems Proceedings Article
In: Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, pp. 869–889, Association for Computing Machinery, Montreal, QC, Canada, 2023, ISBN: 9798400702310.
Human-in-the-Loop Mixup Proceedings Article
In: The 39th Conference on Uncertainty in Artificial Intelligence, 2023.
Individual Privacy Accounting with Gaussian Differential Privacy Proceedings Article
In: The Eleventh International Conference on Learning Representations, 2023.
Interpretable-through-prototypes deepfake detection for diffusion models Proceedings Article
In: 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 467-474, 2023.
Irreducible Curriculum for Language Model Pretraining Proceedings Article
In: NeurIPS Workshop on Attributing Model Behavior at Scale, 2023.
Landmark Attention: Random-Access Infinite Context Length for Transformers Proceedings Article
In: Workshop on Efficient Systems for Foundation Models @ ICML2023, 2023.
Large Class Separation is not what you need for Relational Reasoning-based OOD Detection Proceedings Article
In: International Conference on Image Analysis and Processing, pp. 295–306, Springer 2023.
Learning Counterfactually Invariant Predictors Proceedings Article
In: 2nd Workshop on Formal Verification of Machine Learning, co-located with the 40 th International Conference on Machine Learning, 2023.
Let’s ViCE! Mimicking Human Cognitive Behavior in Image Generation Evaluation Proceedings Article
In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 9306–9312, Association for Computing Machinery, Ottawa ON, Canada, 2023, ISBN: 9798400701085.
Lost in translation: the troubling logics underpinning the embrace of governmental machine-learning based prediction tools for ‘citizen scoring’ Journal Article
In: Global Governance by Data: Infrastructures of Alg, 2023.
Mitigating Robustness Bias: Theoretical Results and Empirical Evidences Proceedings Article
In: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, 2023.
Multiplication-Free Transformer Training via Piecewise Affine Operations Proceedings Article
In: Oh, A.; Naumann, T.; Globerson, A.; Saenko, K.; Hardt, M.; Levine, S. (Ed.): Advances in Neural Information Processing Systems, pp. 8208–8223, Curran Associates, Inc., 2023.
Multitask Learning with No Regret: from Improved Confidence Bounds to Active Learning Proceedings Article
In: Oh, A.; Naumann, T.; Globerson, A.; Saenko, K.; Hardt, M.; Levine, S. (Ed.): Advances in Neural Information Processing Systems, pp. 6770–6781, Curran Associates, Inc., 2023.
Not What You’ve Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection Proceedings Article
In: Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security, pp. 79–90, Association for Computing Machinery, Copenhagen, Denmark, 2023, ISBN: 9798400702600.
On Adversarial Training without Perturbing all Examples Miscellaneous
2023.
On the Efficacy of Differentially Private Few-shot Image Classification Journal Article
In: Transactions on Machine Learning Research, 2023, ISSN: 2835-8856.
On the Informativeness of Supervision Signals Proceedings Article
In: The 39th Conference on Uncertainty in Artificial Intelligence, 2023.
On Adversarial Training without Perturbing all Examples Miscellaneous
2023.
On the Efficacy of Differentially Private Few-shot Image Classification Journal Article
In: Transactions on Machine Learning Research, 2023, ISSN: 2835-8856.
On the Informativeness of Supervision Signals Proceedings Article
In: The 39th Conference on Uncertainty in Artificial Intelligence, 2023.
Private and Collaborative Kaplan-Meier Estimators Proceedings Article
In: Proceedings of the 23rd Workshop on Privacy in the Electronic Society, pp. 212–241, 2023.
PØDA: Prompt-driven Zero-shot Domain Adaptation Proceedings Article
In: ICCV, 2023.
Robust meta-representation learning via global label inference and classification Journal Article
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
SynthCap: Augmenting Transformers with Synthetic Data for Image Captioning Proceedings Article
In: Image Analysis and Processing – ICIAP 2023: 22nd International Conference, ICIAP 2023, Udine, Italy, September 11–15, 2023, Proceedings, Part I, pp. 112–123, Springer-Verlag, Udine, Italy, 2023, ISBN: 978-3-031-43147-0.
Text-DIAE: a self-supervised degradation invariant autoencoder for text recognition and document enhancement Proceedings Article
In: proceedings of the AAAI conference on artificial intelligence, pp. 2330–2338, 2023.
Tight Differential Privacy Guarantees for the Shuffle Model with k-Randomized Response Proceedings Article
In: International Symposium on Foundations and Practice of Security, pp. 440–458, Springer 2023.
Towards Randomized Algorithms and Models that We Can Trust: a Theoretical Perspective Proceedings Article
In: 31st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN, pp. 4–6, 2023.
Towards interpretable-by-design deep learning algorithms Miscellaneous
2023.
STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformers Journal Article
In: arXiv preprint arXiv:2401.05338, 2023.
2022
ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models Proceedings Article
In: 31st USENIX Security Symposium (USENIX Security 22), pp. 4525–4542, USENIX Association, Boston, MA, 2022, ISBN: 978-1-939133-31-1.
Geometric Multimodal Contrastive Representation Learning Proceedings Article
In: Chaudhuri, Kamalika; Jegelka, Stefanie; Song, Le; Szepesvari, Csaba; Niu, Gang; Sabato, Sivan (Ed.): Proceedings of the 39th International Conference on Machine Learning, pp. 17782–17800, PMLR, 2022.
Perspectives on Incorporating Expert Feedback into Model Updates Miscellaneous
2022.
Geometric Multimodal Contrastive Representation Learning Miscellaneous
2022.
Group Meritocratic Fairness in Linear Contextual Bandits Miscellaneous
2022.
Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples Miscellaneous
2022.
Quantitative Evaluation of Systems: 19th International Conference, QEST 2022, Warsaw, Poland, September 12–16, 2022, Proceedings Proceedings
Springer-Verlag, Warsaw, Poland, 2022, ISBN: 978-3-031-16335-7.
Transient-Fault-Aware Design and Training to Enhance DNNs Reliability with Zero-Overhead Proceedings Article
In: 2022 IEEE 28th International Symposium on On-Line Testing and Robust System Design (IOLTS), pp. 1-7, 2022.
UnGANable: Defending Against GAN-based Face Manipulation Miscellaneous
2022.
From Managers to Machines: A Reply to Respondents Journal Article
In: Tilburg Law Review, vol. 27, no. 2, pp. 63–68, 2022.
3DOS: Towards 3D Open Set Learning – Benchmarking and Understanding Semantic Novelty Detection on Point Clouds Proceedings Article
In: Koyejo, S.; Mohamed, S.; Agarwal, A.; Belgrave, D.; Cho, K.; Oh, A. (Ed.): Advances in Neural Information Processing Systems, pp. 21228–21240, Curran Associates, Inc., 2022.
Group Meritocratic Fairness in Linear Contextual Bandits Proceedings Article
In: Koyejo, S.; Mohamed, S.; Agarwal, A.; Belgrave, D.; Cho, K.; Oh, A. (Ed.): Advances in Neural Information Processing Systems, pp. 24392–24404, Curran Associates, Inc., 2022.
Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples Proceedings Article
In: Koyejo, S.; Mohamed, S.; Agarwal, A.; Belgrave, D.; Cho, K.; Oh, A. (Ed.): Advances in Neural Information Processing Systems, pp. 23063–23076, Curran Associates, Inc., 2022.
Private set generation with discriminative information Journal Article
In: Advances in Neural Information Processing Systems, vol. 35, pp. 14678–14690, 2022.
Quantitative Evaluation of Systems: 19th International Conference, QEST 2022, Warsaw, Poland, September 12–16, 2022, Proceedings Book
Springer Nature, 2022.
Robustness guarantees for Bayesian neural networks (invited extended abstract of a keynote speaker) Journal Article
In: 2022.
2021
Establishing the Price of Privacy in Federated Data Trading Book Chapter
In: Lecture Notes in Computer Science, pp. 232–250, Springer International Publishing, 2021, ISSN: 1611-3349.
ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models Miscellaneous
2021.
Establishing the Price of Privacy in Federated Data Trading Book Chapter
In: Dougherty, Joséand M””odersheim Danieland Meseguer (Ed.): Protocols, Strands, and Logic: Essays Dedicated to Joshua Guttman on the Occasion of his 66.66th Birthday, pp. 232–250, Springer International Publishing, Cham, 2021, ISBN: 978-3-030-91631-2.