Scholar
Javier Rando
Google Scholar ID: d_rilUYAAAAJ
Anthropic
Artificial Intelligence
Language Models
Safety
Security
Privacy
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
2,498
H-index
16
i10-index
18
Publications
20
Co-authors
6
list available
Publications
9 items
Self-Propagating Misalignment in LLM Agents, and Why Auditing or Disabling Memory Is Not Enough
2026
Cited
0
Untrusted Content Masking for Web Agents with Security Guarantees
2026
Cited
0
How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
2026
Cited
0
Representations of Text and Images Align From Layer One
2026
Cited
1
Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
2025
Cited
0
AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses
2025
Cited
0
Adversarial ML Problems Are Getting Harder to Solve and to Evaluate
2025
Cited
0
An Adversarial Perspective on Machine Unlearning for AI Safety
2024
Cited
14
Load more
Co-authors
6 total
Florian Tramèr
Assistant Professor of Computer Science, ETH Zurich
Nicholas Carlini
Anthropic
Daniel Paleka
ETH Zurich
Stephen Casper
PhD student, MIT
He He
New York University
Fernando Perez-Cruz
Sr Adviser, Innovation at Bank for International Settlements
