5 accepted papers
Refusal refers to the functional behavior enabling safety-aligned language models to reject harmful or unethical prompts. Following the growing scientific interest in mechanistic interpretability, recent work encoded refusal behavior as a single direction in the model’s latent space; e.g., computed
Ensemble-based black-box transfer attacks optimize adversarial examples on a set of surrogate models, claiming to reach high success rates by querying the (unknown) target model only a few times. In this work, we show that prior evaluations are systematically biased, as such methods are tested only…
The robustness of neural networks against input perturbations with bounded magnitude represents a serious concern in the deployment of deep learning models in safety-critical systems. Recently the scientific community has focused on enhancing certifiable robustness guarantees by crafting \ols neural…
This work presents Z-Mask, an effective and deterministic strategy to improve the adversarial robustness of convolutional networks against physically-realizable adversarial attacks. The presented defense relies on specific Z-score analysis performed on the internal network features to detect and mas…
The use of neural networks in safety-critical systems requires safe and robust models, due to the existence of adversarial attacks. Knowing the minimal adversarial perturbation of any input x, or, equivalently, knowing the distance of x from the classification boundary, allows evaluating the classif…