Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
About me
Ali Shahin Shamsabadi is a Senior Research Scientist at Brave Software working on verifiable, secure and privacy-preserving AI and AI agents.
Posts
portfolio
publications
A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics
Published in IEEE Internet of Things Journal, 2017
A New Algorithm for Training Sparse Autoencoders
Published in 25th European Signal Processing Conference (EUSIPCO), 2017
Privacy-Preserving Deep Inference for Rich User Data on The Cloud
Published in ArXiv, 2017
Deep Private-Feature Extraction
Published in IEEE Transactions on Knowledge and Data Engineering (TKDE), 2018
Private and Scalable Personal Data Analytics using Hybrid Edge-Cloud Deep Learning
Published in IEEE Computer, Special Issue on Mobile and Embedded Deep Learning, 2018
Distributed One-Class Learning
Published in 25th IEEE International Conference on Image Processing (ICIP), 2018
Scene Privacy Protection
Published in 44th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019
QUOTIENT: Two-Party Secure Neural Network Training and Prediction
Published in ACM Conference on Computer and Communications Security (CCS), 2019
Exploiting vulnerabilities of deep neural networks for privacy protection
Published in IEEE Transactions On Multimedia (TMM), 2020
PrivEdge: From Local to Distributed Private Training and Prediction
Published in IEEE Transactions on Information Forensics and Security (TIFS), 2020
EdgeFool: An Adversarial Image Enhancement Filter
Published in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020
DarkneTZ: Towards Model Privacy on the Edge using Trusted Execution Environments
Published in 18th ACM International Conference on Mobile Systems, Applications, and Services (MobiSys), 2020
ColorFool: Semantic Adversarial Colorization
Published in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
FoolHD: Fooling speaker identification by Highly imperceptible adversarial Disturbances
Published in 46th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
Semantically Adversarial Learnable Filters
Published in IEEE Transactions on Image Processing (TIP), 2021
A Zest of LIME: Towards Architecture-Independent Model Distances
Published in The 10th International Conference on Learning Representations (ICLR), 2022
Washing The Unwashable : On The (Im)possibility of Fairwashing Detection
Published in 36th Conference on Neural Information Processing Systems (NeurIPS), 2022
Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregation
Published in 8th IEEE European Symposium on Security and Privacy (EuroS&P), 2023
When the curious abandon honesty: Federated learning is not private
Published in 8th IEEE European Symposium on Security and Privacy (EuroS&P), 2023
Private Multi-Winner Voting for Machine Learning
Published in the 23rd Privacy Enhancing Technologies symposium (PETs), 2023
Differentially Private Speaker Anonymization
Published in the 23rd Privacy Enhancing Technologies symposium (PETs), 2023
Losing Less: A Loss for Differentially Private Deep Learning
Published in the 23rd Privacy Enhancing Technologies symposium (PETs), 2023
Tubes Among Us: Analog Attack on Automatic Speaker Identification
Published in 32nd USENIX Security (USENIX Security), 2023
GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation
Published in 32nd USENIX Security (USENIX Security), 2023
Confidential-PROFITT: Confidential PROof of FaIr Training of Trees
Published in 11th International Conference on Learning Representations (ICLR) notable top 5% of accepted papers , 2023
Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey
Published in ArXiv, 2023
Mnemonist: Locating Model Parameters that Memorize Training Examples
Published in 39th Conference on Uncertainty in Artificial Intelligence (UAI), 2023
Confidential-DPproof : Confidential Proof Of Differentially Private Training
Published in 12th International Conference on Learning Representations (ICLR) spotlight, top 5% , 2024
Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention
Published in 42nd International Conference on Machine Learning (ICML), 2025
Nebula: Efficient, Private and Accurate Histogram Estimation
Published in The 32nd ACM Conference on Computer and Communications Security (CCS), 2025
Context-Aware Membership Inference Attacks against Pre-trained Large Language Models
Published in Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
Membership and Memorization in LLM Knowledge Distillation
Published in Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
Secure and Confidential Certificates of Online Fairness
Published in Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025
Pin the Tail on the Model: Blindfolded Repair of User-Flagged Failures in Text-to-Image Services
Published in Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025
Privacy Practices of Browser Agents
Published in ArXiv, 2025
Frontier AI Auditing: Toward Rigorous Third-Party Assessment of Safety and Security Practices at Leading AI Companies
Published in ArXiv, 2026
SPILLage: Agentic Oversharing on the Web
Published in ArXiv, 2026
AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices
Published in ACM Conference on AI and Agentic Systems (CAIS), 2026
Distributed and Private Textual Data Synthesis from Embeddings
Published in the 27th Privacy Enhancing Technologies symposium (PETs), 2026
teaching
Neural Network
Postgraduate Course, Sharif University of Technology, Computer Engineering, 2016
Machine Learning
Postgraduate Course, Queen Mary University of London, Electrical Engineering and Computer Science, 2018
Lecturer: An Introduction to Trustworthy Machine Learning
Postgraduate Course, International Artificial Intelligence Doctoral Academy (AIDA), 2022
An Overview of Differential Privacy, Membership Inference Attacks, and Federated Learning
Seminar, University of Cambridge, 2023
Collecting Speech and Telemetry Data Privately
Postgraduate Course, Imperial College London, 2024