Daniel Paleka

5 papers · 2023–2025 · 3 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 · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13) 🐣 Hot Topic Early Bird 👥 Mega-Team · Squad

Venues

ICLR (2) NeurIPS (2) ICML (1)

Top co-authors

Florian Tramer (3) Lea Schönherr (1) Fineas Silaghi (1) Neel Nanda (1) Adam Shen (1) Milad Nasr (1) Nicholas Carlini (1) Sahar Abdelnabi (1) Krishnamurthy Dj Dvijotham (1) Mario Fritz (1)

Research topics

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

Keywords

supervised learning (1) model interpretability (1) label noise (1) adversarial attack (1) inductive bia (1) language model (1) security evaluation (1) safety fine-tuning (1) residual stream (1) prompt injection (1) black-box model (1) defense mechanism (1) brier score (1) security vulnerability (1) adversarial vulnerability (1) adversarial risk (1) large language model (1) transformer model (1) weight editing (1) model defense (1)

Papers

Consistency Checks for Language Model Forecasters ICLR 2025 Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition NeurIPS 2024 Refusal in Language Models Is Mediated by a Single Direction NeurIPS 2024 Stealing part of a production language model ICML 2024 A law of adversarial risk, interpolation, and label noise ICLR 2023