Prateek Mittal

Google (United States) — United States

Computer Science · Physical Sciences

44h-index12.1kcitations266works5.02yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Internet Traffic Analysis and Secure E-voting(83), Adversarial Robustness in Machine Learning(70), Privacy-Preserving Technologies in Data(68), Network Security and Intrusion Detection(67), Advanced Malware Detection Techniques(44)

Publications266 total

Adversarial Déjà Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks
arXiv (Cornell University)·2025Open Access
The Model Hears You: Audio Language Model Deployments Should Consider the Principle of Least Privilege
Proceedings of the AAAI/ACM Conference on AI Ethics and Society·2025Open Access
Scaling SCIERA: A Journey Through the Deployment of a Next-generation Network
2025· 3 citedOpen Access
Does More Inference-Time Compute Really Help Robustness?
arXiv (Cornell University)·2025Open Access
What WeChat Knows: Pervasive First-Party Tracking in a Billion-User Super-App Ecosystem
Proceedings on Privacy Enhancing Technologies·2025Open Access
WireWatch: Measuring the Security of Proprietary Network Encryption in the Global Android Ecosystem
2025
Effectively Controlling Reasoning Models through Thinking Intervention
arXiv (Cornell University)·2025Open Access
Differentially Private Image Classification by Learning Priors from Random Processes
Journal of Privacy and Confidentiality·2025· 1 citedOpen Access
The Model Hears You: Audio Language Model Deployments Should Consider the Principle of Least Privilege
arXiv (Cornell University)·2025Open Access
Adapting to Evolving Adversaries with Regularized Continual Robust Training
arXiv (Cornell University)·2025Open Access
Differentially Private Oblivious RAM
2025· 2 cited
List of contributors
Elsevier eBooks·2025
Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
arXiv (Cornell University)·2024Open Access
VFIX: Facilitating Software Maintenance of Smart Contracts via Automatically Fixing Vulnerabilities
2024· 1 cited
Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs
arXiv (Cornell University)·2024Open Access
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
arXiv (Cornell University)·2024· 4 citedOpen Access
AI Risk Management Should Incorporate Both Safety and Security
arXiv (Cornell University)·2024· 1 citedOpen Access
Certifiably Robust RAG against Retrieval Corruption
arXiv (Cornell University)·2024· 4 citedOpen Access
Machine Learning at the Grid Edge: Data-Driven Impedance Models for Model-Free Inverters
IEEE Transactions on Power Electronics·2024· 25 citedOpen Access
Position: Towards Resilience Against Adversarial Examples
arXiv (Cornell University)·2024Open Access
page 1 of 14Next →

Frequent Co-authors

Nikita Borisov(12), Arjun Nitin Bhagoji(8), Neil Zhenqiang Gong(6), Mung Chiang(6), Peng Gao(5), Sanjeev R. Kulkarni(5), Dawn Song(4), Daniel Cullina(4), George Danezis(3), Matthew Caesar(3), Sonia Jahid(3), Chawin Sitawarin(3), Kangkook Jee(3), Shouling Ji(3), Raheem Beyah(3), Vikash Sehwag(3), Xusheng Xiao(3), Liwei Song(3), Supriyo Chakraborty(2), Seraphin Calo(2)