9 citations · 9 across the 8 of their papers we have counts for
9 papers
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…
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…
CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents
Hanna Foerster, Tom Blanchard, Kristina Nikolić +6
AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior. Among proposed defenses, architectural isolation provides the strongest guaran…
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…
Beyond Slow Signs in High-fidelity Model Extraction
Hanna Foerster, Robert Mullins, Ilia Shumailov +1
Deep neural networks, costly to train and rich in intellectual property value, are increasingly threatened by model extraction attacks that compromise their confidentiality. Previo…
Locking Machine Learning Models into Hardware
Eleanor Clifford, Adhithya Saravanan, Harry Langford +5
Modern machine learning (ML) models are expensive IP and business competitiveness often depends on keeping this IP confidential. This in turn restricts how these models are deploye…
Architectural Neural Backdoors from First Principles
Harry Langford, Ilia Shumailov, Yiren Zhao +2
While previous research backdoored neural networks by changing their parameters, recent work uncovered a more insidious threat: backdoors embedded within the definition of the netw…
LLM4DV: Using Large Language Models for Hardware Test Stimuli Generation
Zixi Zhang, Balint Szekely, Pedro Gimenes +5
Hardware design verification (DV) is a process that checks the functional equivalence of a hardware design against its specifications, improving hardware reliability and robustness…
Human-Producible Adversarial Examples
David Khachaturov, Yue Gao, Ilia Shumailov +3
Visual adversarial examples have so far been restricted to pixel-level image manipulations in the digital world, or have required sophisticated equipment such as 2D or 3D printers…