7 papers
Room for Error: Large-Scale Simulation of Over-the-Air Acoustic Attacks
Andrew C. Cullen, Neil G. Marchant, Jiani Xie +4
While voice control is rapidly becoming a ubiquitous vector of human-AI communication, the risks facing these systems remain poorly understood. This is, in part, a product of the d…
What Was That Again? Certified Robustness for Automatic Speech Recognition
Andrew C. Cullen, Neil G. Marchant, Jiani Xie +2
Automatic Speech Recognition systems are notoriously both sensitive to adversarial and benign perturbations. While this has been repeatedly demonstrated using reference datasets, d…
Watermarks Attack Watermarks: Re-Watermarking as a Generic Removal Strategy
Maria Bulychev, Neil G. Marchant, Benjamin I. P. Rubinstein
Watermarking combines an imperceptible change to an input image that will trigger a detector, to assert provenance and protect intellectual property. The literature has shown great…
Where is the Watermark? Interpretable Watermark Detection at the Block Level
Maria Bulychev, Neil G. Marchant, Benjamin I. P. Rubinstein
Recent advances in generative AI have enabled the creation of highly realistic digital content, raising concerns around authenticity, ownership, and misuse. While watermarking has…
On the Bayes Inconsistency of Disagreement Discrepancy Surrogates
Neil G. Marchant, Andrew C. Cullen, Feng Liu +1
Deep neural networks often fail when deployed in real-world contexts due to distribution shift, a critical barrier to building safe and reliable systems. An emerging approach to ad…
AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness
Zhuoqun Huang, Neil G. Marchant, Olga Ohrimenko +1
We consider the problem of certified robustness for sequence classification against edit distance perturbations. Naturally occurring inputs of varying lengths (e.g., sentences in n…