9 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…
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,…
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.…
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…
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…