Florian Tramèr

Computer Science · Physical Sciences

34h-index12.5kcitations143works3.82yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

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

Research Topics

Adversarial Robustness in Machine Learning(58), Privacy-Preserving Technologies in Data(32), Advanced Malware Detection Techniques(18), Cryptography and Data Security(17), Topic Modeling(14)

Publications143 total

Large-scale online deanonymization with LLMs
ArXiv.org·2026Open Access
Large-scale online deanonymization with LLMs
arXiv (Cornell University)·2026Open Access
Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability
arXiv (Cornell University)·2025Open Access
Black-box Optimization of LLM Outputs by Asking for Directions
arXiv (Cornell University)·2025Open Access
The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
arXiv (Cornell University)·2025Open Access
Apertus: Democratizing Open and Compliant LLMs for Global Language Environments
arXiv (Cornell University)·2025· 1 citedOpen Access
Design Patterns for Securing LLM Agents against Prompt Injections
arXiv (Cornell University)·2025Open Access
Membership Inference Attacks on Sequence Models
arXiv (Cornell University)·2025Open Access
Pitfalls in Evaluating Language Model Forecasters
arXiv (Cornell University)·2025Open Access
RealMath: A Continuous Benchmark for Evaluating Language Models on Research-Level Mathematics
arXiv (Cornell University)·2025Open Access
LLMs unlock new paths to monetizing exploits
arXiv (Cornell University)·2025Open Access
Membership Inference Attacks on Sequence Models
2025· 2 cited
SoK: Watermarking for AI-Generated Content
2025· 10 cited
The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
arXiv (Cornell University)·2025Open Access
Position: Membership Inference Attacks Cannot Prove That a Model was Trained on Your Data
2025· 3 cited
AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses
arXiv (Cornell University)·2025Open Access
Adversarial ML Problems Are Getting Harder to Solve and to Evaluate
arXiv (Cornell University)·2025· 1 citedOpen Access
International AI Safety Report
arXiv (Cornell University)·2025· 9 citedOpen Access
Consistency Checks for Language Model Forecasters
arXiv (Cornell University)·2024Open Access
Evaluations of Machine Learning Privacy Defenses are Misleading
2024· 11 citedOpen Access
page 1 of 8Next →

Frequent Co-authors

Nicholas Carlini(18), Dan Boneh(11), Matthew Jagielski(10), Katherine Lee(7), Nicolas Papernot(6), Ari Juels(6), Milad Nasr(6), Jean‐Pierre Hubaux(6), Daphne Ippolito(6), Dawn Song(4), Andreas Terzis(4), Chiyuan Zhang(4), Christopher A. Choquette-Choo(4), Giancarlo Pellegrino(3), Tatsunori Hashimoto(2), Pang Wei Koh(2), Ian Goodfellow(2), Patrick McDaniel(2), Steve Chien(2), Vaggelis Atlidakis(2)