Related papers: Robust Feature Inference: A Test-time Defense Stra…

Pretrained models from self-supervision are prevalently used in fine-tuning downstream tasks faster or for better accuracy. However, gaining robustness from pretraining is left unexplored. We introduce adversarial training into…

We conduct experiments on the impact of increasing inference-time compute in reasoning models (specifically OpenAI o1-preview and o1-mini) on their robustness to adversarial attacks. We find that across a variety of attacks, increased…

Current neural-network-based classifiers are susceptible to adversarial examples. The most empirically successful approach to defending against such adversarial examples is adversarial training, which incorporates a strong self-attack…

As a new programming paradigm, deep learning has expanded its application to many real-world problems. At the same time, deep learning based software are found to be vulnerable to adversarial attacks. Though various defense mechanisms have…

While many defences against adversarial examples have been proposed, finding robust machine learning models is still an open problem. The most compelling defence to date is adversarial training and consists of complementing the training…

While deep neural networks have achieved remarkable success in various computer vision tasks, they often fail to generalize to new domains and subtle variations of input images. Several defenses have been proposed to improve the robustness…

Deep neural networks are discovered to be non-robust when attacked by imperceptible adversarial examples, which is dangerous for it applied into medical diagnostic system that requires high reliability. However, the defense methods that…

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model's incorrect outputs. However,…

Deep networks were recently suggested to face the odds between accuracy (on clean natural images) and robustness (on adversarially perturbed images) (Tsipras et al., 2019). Such a dilemma is shown to be rooted in the inherently higher…

We introduce a feature scattering-based adversarial training approach for improving model robustness against adversarial attacks. Conventional adversarial training approaches leverage a supervised scheme (either targeted or non-targeted) in…

Robust reinforcement learning aims to produce policies that have strong guarantees even in the face of environments/transition models whose parameters have strong uncertainty. Existing work uses value-based methods and the usual primitive…

There has been emerging interest to use transductive learning for adversarial robustness (Goldwasser et al., NeurIPS 2020; Wu et al., ICML 2020). Compared to traditional "test-time" defenses, these defense mechanisms "dynamically retrain"…

Deep neural networks (DNNs) are highly susceptible to adversarial samples, raising concerns about their reliability in safety-critical tasks. Currently, methods of evaluating adversarial robustness are primarily categorized into…

Face recognition (FR) has recently made substantial progress and achieved high accuracy on standard benchmarks. However, it has raised security concerns in enormous FR applications because deep CNNs are unusually vulnerable to adversarial…

Despite its popularity, deep neural networks are easily fooled. To alleviate this deficiency, researchers are actively developing new training strategies, which encourage models that are robust to small input perturbations. Several…

Existing deep neural networks, say for image classification, have been shown to be vulnerable to adversarial images that can cause a DNN misclassification, without any perceptible change to an image. In this work, we propose shock absorbing…

Recent work has put forth the hypothesis that adversarial vulnerabilities in neural networks are due to them overusing "non-robust features" inherent in the training data. We show empirically that for PGD-attacks, there is a training stage…

Robust training methods typically defend against specific attack types, such as Lp attacks with fixed budgets, and rarely account for the fact that defenders may encounter new attacks over time. A natural solution is to adapt the defended…

Deep learning models are prone to being fooled by imperceptible perturbations known as adversarial attacks. In this work, we study how equipping models with Test-time Transformation Ensembling (TTE) can work as a reliable defense against…

Nowadays, pretrained models are increasingly used as general-purpose backbones and adapted at test-time to downstream environments where target data are scarce and unlabeled. While this paradigm has proven effective for improving clean…