AI safety researcher

Ilia Shumailov

Google Scholar dblp OpenReview ORCID

Last 12 months11 papers

Defenses 2Attacks 1

AI safety papers from the last year

On this site: 69 papers

October 2026

Can CaMeLs Talk? Securing Multi-Agent Systems Against Indirect Prompt Injection Attacks
Oct 5DefensesarXiv ↗
Securing Computer-Use Agents Against Branch Steering Attacks
Oct 1DefensesarXiv ↗

August 2026

CodeMechanic: Bug-Property-Guided Program Mitigation
Aug 23arXiv ↗
Stealing Reasoning Traces from Proprietary LLM APIs
Aug 10AttacksarXiv ↗

July 2026

Open Technical Problems in Open-Weight AI Model Risk Management
Jul 1arXiv ↗

May 2026

Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots
May 28arXiv ↗

April 2026

Quantamination: Dynamic Quantization Leaks Your Data Across the Batch
Apr 29arXiv ↗

March 2026

Kraken: Higher-order EM Side-Channel Attacks on DNNs in Near and Far Field
Mar 3arXiv ↗

January 2026

December 2025

ceLLMate: Sandboxing Browser AI Agents
Dec 14arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.