Profiles2016-2026
Prateek Mittal
Princeton University
34Papers
22Last author
64Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers34
- Red-Teaming NSFW Image Classifiers as Text-to-Image SafeguardsAuthor 8 of 9ACL Findings 2026 · 1 citation
- ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-SearchAuthor 5 of 6NeurIPS 2025 · 26 citations
- On Evaluating the Durability of Safeguards for Open-Weight LLMsAuthor 9 of 10ICLR 2025
- PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial PatchesAuthor 3 of 3CVPR 2025
- Safety Alignment Should be Made More Than Just a Few Tokens DeepAuthor 6 of 7ICLR 2025
- WireWatch: Measuring the Security of Proprietary Network Encryption in the Global Android EcosystemAuthor 4 of 5S&P 2025
- Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!Author 6 of 7ICLR 2024 · 1,104 citations
- GREATS: Online Selection of High-Quality Data for LLM Training in Every IterationAuthor 4 of 5NeurIPS 2024 · 91 citations
- BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input DetectionAuthor 6 of 6ICLR 2024 · 20 citations
- A Privacy-Friendly Approach to Data ValuationAuthor 5 of 5NeurIPS 2023 · 12 citations
- Characterizing the Optimal 0-1 Loss for Multi-class Classification with a Test-time AttackerAuthor 7 of 7NeurIPS 2023 · 6 citations
- A Randomized Approach to Tight Privacy AccountingAuthor 5 of 5NeurIPS 2023
- ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic MaskingAuthor 4 of 4S&P 2023
- Revisiting the Assumption of Latent Separability for Backdoor DefensesAuthor 5 of 5ICLR 2023
- Understanding Robust Learning through the Lens of Representation SimilaritiesAuthor 5 of 6NeurIPS 2022 · 20 citations
- Formulating Robustness Against Unforeseen AttacksAuthor 3 of 3NeurIPS 2022 · 12 citations
- Renyi Differential Privacy of Propose-Test-Release and Applications to Private and Robust Machine LearningAuthor 5 of 5NeurIPS 2022 · 6 citations
- Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble ArchitectureAuthor 7 of 7USENIX Security 2022
- Systematic Evaluation of Privacy Risks of Machine Learning ModelsAuthor 2 of 2USENIX Security 2021 · 483 citations
- SSD: A Unified Framework for Self-Supervised Outlier DetectionAuthor 3 of 3ICLR 2021 · 410 citations
- Enabling Efficient Cyber Threat Hunting With Cyber Threat IntelligenceAuthor 7 of 9ICDE 2021 · 124 citations
- DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding AttacksAuthor 2 of 2CCS 2021 · 58 citations
- CLAPS: Client-Location-Aware Path Selection in TorAuthor 4 of 5CCS 2020 · 23 citations
- Privacy Risks of Securing Machine Learning Models against Adversarial ExamplesAuthor 3 of 3CCS 2019 · 293 citations
- Robust Website Fingerprinting Through the Cache Occupancy ChannelAuthor 5 of 7USENIX Security 2019 · 159 citations
- SICO: Surgical Interception Attacks by Manipulating BGP CommunitiesAuthor 4 of 4CCS 2019 · 51 citations
- BlackIoT: IoT Botnet of High Wattage Devices Can Disrupt the Power GridAuthor 2 of 3USENIX Security 2018 · 348 citations
- Towards a Timely Causality Analysis for Enterprise SecurityAuthor 8 of 8NDSS 2018 · 177 citations
- SAQL: A Stream-based Query System for Real-Time Abnormal System Behavior DetectionAuthor 9 of 9USENIX Security 2018 · 122 citations
- MVG Mechanism: Differential Privacy under Matrix-Valued QueryAuthor 4 of 4CCS 2018 · 55 citations
Showing the 30 most recent indexed papers.
