5 papers
Get RICH or Die Scaling: Profitably Trading Inference Compute for Robustness
Tavish McDonald, Bo Lei, Stanislav Fort +2
Test-time reasoning has raised benchmark performances and even shown promise in addressing the historically intractable problem of making models robust to adversarially out-of-dist…
Solving adversarial examples requires solving exponential misalignment
Alessandro Salvatore, Stanislav Fort, Surya Ganguli
Adversarial attacks - input perturbations imperceptible to humans that fool neural networks - remain both a persistent failure mode in machine learning, and a phenomenon with myste…
Representations of Text and Images Align From Layer One
Evžen Wybitul, Javier Rando, Florian Tramèr +1
We show that for a variety of concepts in adapter-based vision-language models, the representations of their images and their text descriptions are meaningfully aligned from the ve…
Direct Ascent Synthesis: Revealing Hidden Generative Capabilities in Discriminative Models
Stanislav Fort, Jonathan Whitaker
We demonstrate that discriminative models inherently contain powerful generative capabilities, challenging the fundamental distinction between discriminative and generative archite…
A Note on Implementation Errors in Recent Adaptive Attacks Against Multi-Resolution Self-Ensembles
Stanislav Fort
This note documents an implementation issue in recent adaptive attacks (Zhang et al. [2024]) against the multi-resolution self-ensemble defense (Fort and Lakshminarayanan [2024]).…