Shoumik Saha

5 papers · 2024–2025 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13) 🐣 Hot Topic Early Bird 👑 Triple Crown

Venues

ACL (1) EMNLP (1) ICLR (1) ICML (1) NeurIPS (1)

Top co-authors

Soheil Feizi (4) Priyatham Kattakinda (2) Vinu Sankar Sadasivan (2) Gaurang Sriramanan (2) Wenxiao Wang (1) Sharmila Duppala (1) Saad Mohammad Abrar (1) Tudor Dumitras (1) Yigitcan Kaya (1) Zhicheng Liu (1)

Research topics

Artificial Intelligence (5) Core AI (5) Machine Learning (3) Natural Language Processing (2) Learning Types (2) Deep Learning (1) Application Areas (1) Applications (1) Core Methods (1) Models (1) Optimization & Theory (1) Resources & Methods (1)

Keywords

large language model (2) certified robustness (1) text classification (1) visual question answering (1) machine-generated text detection (1) data visualization (1) static analysis (1) malware detection (1) adversarial attack (1) hidden state (1) adversarial defense (1) vision-language model (1) retrieval-augmented generation (1) hallucination detection (1) internal state analysis (1) white-box setting (1) black-box setting (1) hidden state analysis (1) membership inference (1) attention map (1)

Papers

Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writing ACL 2025 ProcVQA: Benchmarking the Effects of Structural Properties in Mined Process Visualizations on Vision–Language Model Performance EMNLP 2025 DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness ICLR 2024 Fast Adversarial Attacks on Language Models In One GPU Minute ICML 2024 LLM-Check: Investigating Detection of Hallucinations in Large Language Models NeurIPS 2024