conftrace_
← Authors

Daniel Paleka

5 papers · 2023–2025 · 3 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+1 more ↓ 🌍 Conference Polyglot (3) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (15)
👥 Mega-Team (21)

Conferences

ICLR (2) NIPS (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)

Keywords

model interpretability (1) adversarial attack (1) security evaluation (1) safety fine-tuning (1) residual stream (1) prompt injection (1) defense mechanism (1) security vulnerability (1) large language model (1) weight editing (1) model defense (1) refusal direction (1)

Papers

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