121 citations · 505 across the 31 of their papers we have counts for
35 papers
Thinking into the Future: Latent Lookahead Training for Transformers
Lorenzo Noci, Gregor Bachmann, Seyed-Mohsen Moosavi-Dezfooli +1
Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to…
On the Anisotropy of Score-Based Generative Models
Andreas Floros, Seyed-Mohsen Moosavi-Dezfooli, Pier Luigi Dragotti
We investigate the role of network architecture in shaping the inductive biases of modern score-based generative models. To this end, we introduce the Score Anisotropy Directions (…
Rewriting the Budget: A General Framework for Black-Box Attacks Under Cost Asymmetry
Mahdi Salmani, Alireza Abdollahpoorrostam, Seyed-Mohsen Moosavi-Dezfooli
Traditional decision-based black-box adversarial attacks on image classifiers aim to generate adversarial examples by slightly modifying input images while keeping the number of qu…
Trustworthy Image Super-Resolution via Generative Pseudoinverse
Andreas Floros, Seyed-Mohsen Moosavi-Dezfooli, Pier Luigi Dragotti
We consider the problem of trustworthy image restoration, taking the form of a constrained optimization over the prior density. To this end, we develop generative models for the ta…
LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders
Borna Khodabandeh, Amirabbas Afzali, Amirhossein Afsharrad +4
Visual encoders have become fundamental components in modern computer vision pipelines. However, ensuring robustness against adversarial perturbations remains a critical challenge.…
Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attribution
Andreas Floros, Seyed-Mohsen Moosavi-Dezfooli, Pier Luigi Dragotti
Diffusion models have transformed image synthesis through iterative denoising, by defining trajectories from noise to coherent data. While their capabilities are widely celebrated,…
Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture
Sajad Movahedi, Antonio Orvieto, Seyed-Mohsen Moosavi-Dezfooli
In this paper, we propose the , which argues that the input space curvature of a neural network remains invariant under transformati…
Certified Human Trajectory Prediction
Mohammadhossein Bahari, Saeed Saadatnejad, Amirhossein Askari Farsangi +2
Predicting human trajectories is essential for the safe operation of autonomous vehicles, yet current data-driven models often lack robustness in case of noisy inputs such as adver…
How to choose your best allies for a transferable attack?
Thibault Maho, Seyed-Mohsen Moosavi-Dezfooli, Teddy Furon
The transferability of adversarial examples is a key issue in the security of deep neural networks. The possibility of an adversarial example crafted for a source model fooling ano…
Revisiting DeepFool: generalization and improvement
Alireza Abdollahpoorrostam, Mahed Abroshan, Seyed-Mohsen Moosavi-Dezfooli
Deep neural networks have been known to be vulnerable to adversarial examples, which are inputs that are modified slightly to fool the network into making incorrect predictions. Th…
The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training
Junhao Dong, Seyed-Mohsen Moosavi-Dezfooli, Jianhuang Lai +1
Although current deep learning techniques have yielded superior performance on various computer vision tasks, yet they are still vulnerable to adversarial examples. Adversarial tra…
PRIME: A few primitives can boost robustness to common corruptions
Apostolos Modas, Rahul Rade, Guillermo Ortiz-Jiménez +2
Despite their impressive performance on image classification tasks, deep networks have a hard time generalizing to unforeseen corruptions of their data. To fix this vulnerability,…
Vehicle trajectory prediction works, but not everywhere
Mohammadhossein Bahari, Saeed Saadatnejad, Ahmad Rahimi +4
Vehicle trajectory prediction is nowadays a fundamental pillar of self-driving cars. Both the industry and research communities have acknowledged the need for such a pillar by prov…
Are socially-aware trajectory prediction models really socially-aware?
Saeed Saadatnejad, Mohammadhossein Bahari, Pedram Khorsandi +3
Our field has recently witnessed an arms race of neural network-based trajectory predictors. While these predictors are at the core of many applications such as autonomous navigati…
Adversarial training may be a double-edged sword
Ali Rahmati, Seyed-Mohsen Moosavi-Dezfooli, Huaiyu Dai
Adversarial training has been shown as an effective approach to improve the robustness of image classifiers against white-box attacks. However, its effectiveness against black-box…
What can linearized neural networks actually say about generalization?
Guillermo Ortiz-Jiménez, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard
For certain infinitely-wide neural networks, the neural tangent kernel (NTK) theory fully characterizes generalization, but for the networks used in practice, the empirical NTK onl…
Understanding Catastrophic Overfitting in Adversarial Training
Peilin Kang, Seyed-Mohsen Moosavi-Dezfooli
Recently, FGSM adversarial training is found to be able to train a robust model which is comparable to the one trained by PGD but an order of magnitude faster. However, there is a…
Uniform Convergence, Adversarial Spheres and a Simple Remedy
Gregor Bachmann, Seyed-Mohsen Moosavi-Dezfooli, Thomas Hofmann
Previous work has cast doubt on the general framework of uniform convergence and its ability to explain generalization in neural networks. By considering a specific dataset, it was…
A neural anisotropic view of underspecification in deep learning
Guillermo Ortiz-Jimenez, Itamar Franco Salazar-Reque, Apostolos Modas +2
The underspecification of most machine learning pipelines means that we cannot rely solely on validation performance to assess the robustness of deep learning systems to naturally…
Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness
Guillermo Ortiz-Jimenez, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli +1
Driven by massive amounts of data and important advances in computational resources, new deep learning systems have achieved outstanding results in a large spectrum of applications…
Neural Anisotropy Directions
Guillermo Ortiz-Jimenez, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli +1
In this work, we analyze the role of the network architecture in shaping the inductive bias of deep classifiers. To that end, we start by focusing on a very simple problem, i.e., c…
GeoDA: a geometric framework for black-box adversarial attacks
Ali Rahmati, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard +1
Adversarial examples are known as carefully perturbed images fooling image classifiers. We propose a geometric framework to generate adversarial examples in one of the most challen…
Hold me tight! Influence of discriminative features on deep network boundaries
Guillermo Ortiz-Jimenez, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli +1
Important insights towards the explainability of neural networks reside in the characteristics of their decision boundaries. In this work, we borrow tools from the field of adversa…
A geometry-inspired decision-based attack
Yujia Liu, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard
Deep neural networks have recently achieved tremendous success in image classification. Recent studies have however shown that they are easily misled into incorrect classification…