Get started
Author

Thomas Rivasseau

Observed name: Rivasseau, Thomas
Institution: McGill University
Observed institution: McGill University
OpenAlex ID: A5120411401
Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tuning
2026 · Rivasseau, Thomas · arXiv (Cornell University)
PDF
I must delete the evidence: AI Agents Explicitly Cover up Fraud and Violent Crime
2026 · Rivasseau, Thomas · arXiv (Cornell University)
PDF
ICML Conference Submission experiment transcripts
2026 · Rivasseau, Thomas, Fung, Benjamin C.M. · Figshare
Invasive Context Engineering to Control Large Language Models
2025 · Rivasseau, Thomas · arXiv (Cornell University)
PDF
LLM Reinforcement in Context
2025 · Rivasseau, Thomas · arXiv (Cornell University)
PDF
Hash chaining degrades security at Facebook
2025 · Rivasseau, Thomas · arXiv (Cornell University)
PDF
Works count: 6
Citation count:
H-index:
I10-index:
Year
Topic
Type