2 citations · 2 across the 7 of their papers we have counts for
5 papers · 1 filter
Securing Computer-Use Agents Against Branch Steering Attacks
Giulio Zingrillo, Hanna Foerster, Ilia Shumailov +2
Modern Computer Use Agents (CUAs) directly interact with graphical user interfaces and execute third-party web tools, exposing them to indirect prompt injection across every render…
AI Agents Enable Adaptive Computer Worms
Jonas Guan, Tom Blanchard, Hanna Foerster +3
A computer worm is malware that spreads on a network by replicating itself from one machine to another. Traditional worms, like WannaCry, exploited predetermined vulnerabilities, a…
Quantamination: Dynamic Quantization Leaks Your Data Across the Batch
Hanna Foerster, Ilia Shumailov, Cheng Zhang +3
Dynamic quantization emerged as a practical approach to increase the utilization and efficiency of the machine learning serving flow. Unlike static quantization, which applies quan…
Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models
Harsh Chaudhari, Ethan Rathbun, Hanna Foerster +5
Chain-of-Thought (CoT) reasoning has emerged as a powerful technique for enhancing large language models' capabilities by generating intermediate reasoning steps for complex tasks.…
Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated
Hanna Foerster, Ilia Shumailov, Yiren Zhao +4
Early research into data poisoning attacks against Large Language Models (LLMs) demonstrated the ease with which backdoors could be injected. More recent LLMs add step-by-step reas…