9 papers
ALLUDE: A Unified Evaluation System for Configurable Attacks in Differentiable Environments
Mansi Phute, Alexander Greenhalgh, Matthew Hull +8
Adversarial attacks against vision models like object detectors are often evaluated under limited conditions, leaving their performance under-characterized. Bridging simulation and…
UNDREAM: Bridging Differentiable Rendering and Photorealistic Simulation for End-to-end Adversarial Attacks
Mansi Phute, Matthew Hull, Haoran Wang +6
Deep learning models deployed in safety critical applications like autonomous driving use simulations to test their robustness against adversarial attacks in realistic conditions.…
VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models
Ravikumar Balakrishnan, Mansi Phute
As Vision Language Models (VLMs) are deployed across safety-critical applications, understanding and controlling their behavioral patterns has become increasingly important. Existi…
VISOR: Visual Input-based Steering for Output Redirection in Vision-Language Models
Mansi Phute, Ravikumar Balakrishnan
Vision Language Models (VLMs) are increasingly being used in a broad range of applications, bringing their security and behavioral control to the forefront. While existing approach…
Community-Specific Slang and Entity Detection via Semantic Shift in Fine-Tuned Language Models
Julia Kruk, Sanchita Porwal, Amitrajit Bhattacharjee +1
We propose an unsupervised method of resolving slang, unique entities, and folklore from online communities by isolating words in the lexicon that have the highest magnitude of sem…
ComplicitSplat: Downstream Models are Vulnerable to Blackbox Attacks by 3D Gaussian Splat Camouflages
Matthew Hull, Haoyang Yang, Pratham Mehta +8
As 3D Gaussian Splatting (3DGS) gains rapid adoption in safety-critical tasks for efficient novel-view synthesis from static images, how might an adversary tamper images to cause h…